sentiment analysis bachelor thesis

• My Shodhganga
• Receive email updates
• Edit Profile

Shodhganga : a reservoir of Indian theses @ INFLIBNET

• Shodhganga@INFLIBNET
• Anna University
• Faculty of Science and Humanities

Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

The Future of AI Research: 20 Thesis Ideas for Undergraduate Students in Machine Learning and Deep Learning for 2023!

A comprehensive guide for crafting an original and innovative thesis in the field of ai..

By Aarafat Islam on 2023-01-11

“The beauty of machine learning is that it can be applied to any problem you want to solve, as long as you can provide the computer with enough examples.” — Andrew Ng

This article provides a list of 20 potential thesis ideas for an undergraduate program in machine learning and deep learning in 2023. Each thesis idea includes an  introduction , which presents a brief overview of the topic and the  research objectives . The ideas provided are related to different areas of machine learning and deep learning, such as computer vision, natural language processing, robotics, finance, drug discovery, and more. The article also includes explanations, examples, and conclusions for each thesis idea, which can help guide the research and provide a clear understanding of the potential contributions and outcomes of the proposed research. The article also emphasized the importance of originality and the need for proper citation in order to avoid plagiarism.

1. Investigating the use of Generative Adversarial Networks (GANs) in medical imaging:  A deep learning approach to improve the accuracy of medical diagnoses.

Introduction:  Medical imaging is an important tool in the diagnosis and treatment of various medical conditions. However, accurately interpreting medical images can be challenging, especially for less experienced doctors. This thesis aims to explore the use of GANs in medical imaging, in order to improve the accuracy of medical diagnoses.

2. Exploring the use of deep learning in natural language generation (NLG): An analysis of the current state-of-the-art and future potential.

Introduction:  Natural language generation is an important field in natural language processing (NLP) that deals with creating human-like text automatically. Deep learning has shown promising results in NLP tasks such as machine translation, sentiment analysis, and question-answering. This thesis aims to explore the use of deep learning in NLG and analyze the current state-of-the-art models, as well as potential future developments.

3. Development and evaluation of deep reinforcement learning (RL) for robotic navigation and control.

Introduction:  Robotic navigation and control are challenging tasks, which require a high degree of intelligence and adaptability. Deep RL has shown promising results in various robotics tasks, such as robotic arm control, autonomous navigation, and manipulation. This thesis aims to develop and evaluate a deep RL-based approach for robotic navigation and control and evaluate its performance in various environments and tasks.

4. Investigating the use of deep learning for drug discovery and development.

Introduction:  Drug discovery and development is a time-consuming and expensive process, which often involves high failure rates. Deep learning has been used to improve various tasks in bioinformatics and biotechnology, such as protein structure prediction and gene expression analysis. This thesis aims to investigate the use of deep learning for drug discovery and development and examine its potential to improve the efficiency and accuracy of the drug development process.

5. Comparison of deep learning and traditional machine learning methods for anomaly detection in time series data.

Introduction:  Anomaly detection in time series data is a challenging task, which is important in various fields such as finance, healthcare, and manufacturing. Deep learning methods have been used to improve anomaly detection in time series data, while traditional machine learning methods have been widely used as well. This thesis aims to compare deep learning and traditional machine learning methods for anomaly detection in time series data and examine their respective strengths and weaknesses.

Photo by  Joanna Kosinska  on  Unsplash

6. Use of deep transfer learning in speech recognition and synthesis.

Introduction:  Speech recognition and synthesis are areas of natural language processing that focus on converting spoken language to text and vice versa. Transfer learning has been widely used in deep learning-based speech recognition and synthesis systems to improve their performance by reusing the features learned from other tasks. This thesis aims to investigate the use of transfer learning in speech recognition and synthesis and how it improves the performance of the system in comparison to traditional methods.

7. The use of deep learning for financial prediction.

Introduction:  Financial prediction is a challenging task that requires a high degree of intelligence and adaptability, especially in the field of stock market prediction. Deep learning has shown promising results in various financial prediction tasks, such as stock price prediction and credit risk analysis. This thesis aims to investigate the use of deep learning for financial prediction and examine its potential to improve the accuracy of financial forecasting.

8. Investigating the use of deep learning for computer vision in agriculture.

Introduction:  Computer vision has the potential to revolutionize the field of agriculture by improving crop monitoring, precision farming, and yield prediction. Deep learning has been used to improve various computer vision tasks, such as object detection, semantic segmentation, and image classification. This thesis aims to investigate the use of deep learning for computer vision in agriculture and examine its potential to improve the efficiency and accuracy of crop monitoring and precision farming.

9. Development and evaluation of deep learning models for generative design in engineering and architecture.

Introduction:  Generative design is a powerful tool in engineering and architecture that can help optimize designs and reduce human error. Deep learning has been used to improve various generative design tasks, such as design optimization and form generation. This thesis aims to develop and evaluate deep learning models for generative design in engineering and architecture and examine their potential to improve the efficiency and accuracy of the design process.

10. Investigating the use of deep learning for natural language understanding.

Introduction:  Natural language understanding is a complex task of natural language processing that involves extracting meaning from text. Deep learning has been used to improve various NLP tasks, such as machine translation, sentiment analysis, and question-answering. This thesis aims to investigate the use of deep learning for natural language understanding and examine its potential to improve the efficiency and accuracy of natural language understanding systems.

Photo by  UX Indonesia  on  Unsplash

11. Comparing deep learning and traditional machine learning methods for image compression.

Introduction:  Image compression is an important task in image processing and computer vision. It enables faster data transmission and storage of image files. Deep learning methods have been used to improve image compression, while traditional machine learning methods have been widely used as well. This thesis aims to compare deep learning and traditional machine learning methods for image compression and examine their respective strengths and weaknesses.

12. Using deep learning for sentiment analysis in social media.

Introduction:  Sentiment analysis in social media is an important task that can help businesses and organizations understand their customers’ opinions and feedback. Deep learning has been used to improve sentiment analysis in social media, by training models on large datasets of social media text. This thesis aims to use deep learning for sentiment analysis in social media, and evaluate its performance against traditional machine learning methods.

13. Investigating the use of deep learning for image generation.

Introduction:  Image generation is a task in computer vision that involves creating new images from scratch or modifying existing images. Deep learning has been used to improve various image generation tasks, such as super-resolution, style transfer, and face generation. This thesis aims to investigate the use of deep learning for image generation and examine its potential to improve the quality and diversity of generated images.

14. Development and evaluation of deep learning models for anomaly detection in cybersecurity.

Introduction:  Anomaly detection in cybersecurity is an important task that can help detect and prevent cyber-attacks. Deep learning has been used to improve various anomaly detection tasks, such as intrusion detection and malware detection. This thesis aims to develop and evaluate deep learning models for anomaly detection in cybersecurity and examine their potential to improve the efficiency and accuracy of cybersecurity systems.

15. Investigating the use of deep learning for natural language summarization.

Introduction:  Natural language summarization is an important task in natural language processing that involves creating a condensed version of a text that preserves its main meaning. Deep learning has been used to improve various natural language summarization tasks, such as document summarization and headline generation. This thesis aims to investigate the use of deep learning for natural language summarization and examine its potential to improve the efficiency and accuracy of natural language summarization systems.

Photo by  Windows  on  Unsplash

16. Development and evaluation of deep learning models for facial expression recognition.

Introduction:  Facial expression recognition is an important task in computer vision and has many practical applications, such as human-computer interaction, emotion recognition, and psychological studies. Deep learning has been used to improve facial expression recognition, by training models on large datasets of images. This thesis aims to develop and evaluate deep learning models for facial expression recognition and examine their performance against traditional machine learning methods.

17. Investigating the use of deep learning for generative models in music and audio.

Introduction:  Music and audio synthesis is an important task in audio processing, which has many practical applications, such as music generation and speech synthesis. Deep learning has been used to improve generative models for music and audio, by training models on large datasets of audio data. This thesis aims to investigate the use of deep learning for generative models in music and audio and examine its potential to improve the quality and diversity of generated audio.

18. Study the comparison of deep learning models with traditional algorithms for anomaly detection in network traffic.

Introduction:  Anomaly detection in network traffic is an important task that can help detect and prevent cyber-attacks. Deep learning models have been used for this task, and traditional methods such as clustering and rule-based systems are widely used as well. This thesis aims to compare deep learning models with traditional algorithms for anomaly detection in network traffic and analyze the trade-offs between the models in terms of accuracy and scalability.

19. Investigating the use of deep learning for improving recommender systems.

Introduction:  Recommender systems are widely used in many applications such as online shopping, music streaming, and movie streaming. Deep learning has been used to improve the performance of recommender systems, by training models on large datasets of user-item interactions. This thesis aims to investigate the use of deep learning for improving recommender systems and compare its performance with traditional content-based and collaborative filtering approaches.

20. Development and evaluation of deep learning models for multi-modal data analysis.

Introduction:  Multi-modal data analysis is the task of analyzing and understanding data from multiple sources such as text, images, and audio. Deep learning has been used to improve multi-modal data analysis, by training models on large datasets of multi-modal data. This thesis aims to develop and evaluate deep learning models for multi-modal data analysis and analyze their potential to improve performance in comparison to single-modal models.

I hope that this article has provided you with a useful guide for your thesis research in machine learning and deep learning. Remember to conduct a thorough literature review and to include proper citations in your work, as well as to be original in your research to avoid plagiarism. I wish you all the best of luck with your thesis and your research endeavors!

Continue Learning

Understanding the mechanics: how ai art generators produce unique artworks, the best free ai tool for image generation: not midjourney, midjourney lighting guide: tips and advice, wondershare virbo reviewed: the best ai video creator, how ai is altering our memories and perception of reality, prompt engineering: how to turn your words into works of art.

https://doi.org/10.18452/20866

File(s) under embargo

until file(s) become available

From Performance to Trust: Improving the Reliability of Pre-trained Language Models

Degree grantor, degree level, degree name, committee member, thesis type, usage metrics.

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

Transferring sentiment cross-lingually within and across same-family languages.

1. Introduction

2. research questions and hypotheses.

• A cross-lingual transfer is more successful for typologically similar languages than for typologically different languages.
• A large annotated dataset in a distant-family language can overcome typological differences, unlike a small annotated dataset in a close-family language.
• Initially, we propose a framework for unified deep learning that utilizes existing data labels from high-resource languages on low-resource datasets. We conduct rigorous experiments on languages within the same language family. We investigate how effectively sentiment classification abilities could be transferred.
• Second, we demonstrate that, given multiple large-scale training datasets, our framework is superior to a straightforward setup for fine-tuning. Finally, we devise the optimal method for jointly training sentiment analysis systems in order to address the issue of insufficient resources for target languages.

3. Languages in the Study

4. related work, 4.1. sentiment analysis, 4.2. sentiment analysis in slavic languages, 4.3. cross-lingual sentiment analysis, sentiment analysis datasets.

• Bulgarian: The Cinexio [ 51 ] dataset is composed of film reviews with 11-point star ratings: 0 (negative), 0.5, 1, … 4.5, 5 (positive). Other meta-features included in the dataset are film length, director, actors, genre, country, and various scores.
• Croatian: Pauza [ 68 ] contains restaurant reviews from Pauza.hr4, the largest food ordering website in Croatia. Each review is assigned an opinion rating ranging from 0.5 (worst) to 6 (best). User-assigned ratings are the benchmark for labels. The dataset also contains opinionated aspects.
• Czech: The CSFD [ 108 ] dataset was influenced by Pang et al. [ 109 ]. It includes film reviews from the Czech Movie Database ( http://www.csfd.cz accessed on 10 September 2023). Every review is classified as either positive, neutral, or negative.
• English: The Multilingual Amazon Reviews Corpus (MARC) is a large collection of Amazon reviews [ 110 ]. The corpus contains reviews written in Chinese, English, Japanese, German, French, and Spanish. Each review is assigned a maximum of five stars. Each record contains the review text, the title, the star rating, and product-related metadata.
• Polish: The Wroclaw Corpus of Consumer Reviews Sentiment [ 77 ] is a multi-domain dataset of Polish reviews from the domains of schools, medicine, hotels, and products. The texts have been annotated at both the sentence level and the text body level. The reviews are labeled as follows: [+m] represents a strong positive; [+s] represents a weak positive; [−m] represents a strong negative; [−s] represents a weak negative; [amb] represents ambiguity; and [0] represents neutrality.
• Russian: The ROMIP-12 dataset [ 80 ] is composed of news-based opinions, which are excerpts of the direct and indirect speech published in news articles. Politics, economics, sports, and the arts are just some of the diverse subject areas covered. This dataset contains speech classified as positive, neutral, or negative.
• Slovak: The Review3 [ 111 ] is composed of customer evaluations of a variety of services. The dataset is categorized using the 1–3 and 1–5 scales.
• Slovene: The Opinion corpus of Slovene web commentaries KKS 1.001 [ 90 ] includes web commentaries on various topics (business, politics, sports, etc.) from four Slovene web portals (RtvSlo, 24ur, Finance, and Reporter). Each instance within the dataset is tagged with one of the three labels (negative, neutral, or positive).

6. Methodology

• Used directly to train the model. Here, the source language serves as the target language as well (like Bulgarian).
• Combined with a single dataset from a distant language family (like English).
• Combined with a single dataset from a different sub-branch of the same language family (like Russian, Polish, or Czech).
• Merged with a number of low-resource language datasets (Croatian, Slovak, and Slovene).

6.1. Model Details

6.2. training.

• Using only source-language data for fine-tuning. This is the conventional transfer learning setup performed by a source-language fine-tuning classifier. A zero-shot test is administered to the trained model using a test of the target language. We guided the training process using the target language’s validation set. We projected labels from a fine-grained class of 5 classes to a coarse-grained class of 3 classes due to the possibility that the target language dataset labels do not match the source language.
• Fine-tuning with a single source and target language. We sampled training sets from multiple languages and jointly trained the classifier. We utilized datasets from distantly related languages and vice versa.
• Fine-tuning using multiple datasets derived from a single source and target language. This is a multilingual environment with multiple sources.
• Fine-tuning with the Latin versions of the Bulgarian and Russian datasets.

7. Experimental Setup

Training details, 8. results and discussion, 8.1. results, 8.2. error analysis, 8.3. language representations in xlm-roberta, 9. conclusions, author contributions, institutional review board statement, informed consent statement, data availability statement, conflicts of interest, abbreviations.

• Go, A.; Bhayani, R.; Huang, L. Twitter Sentiment Classification Using Distant Supervision ; CS224N Project Report; Stanford University: Stanford, CA, USA, 2009. [ Google Scholar ]
• Nakov, P.; Rosenthal, S.; Kozareva, Z.; Stoyanov, V.; Ritter, A.; Wilson, T. SemEval-2013 Task 2: Sentiment Analysis in Twitter. In Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), Atlanta, GA, USA, 14–15 June 2013; pp. 14–15. [ Google Scholar ]
• Saif, H.; Fernández, M.; He, Y.; Alani, H. Evaluation datasets for Twitter sentiment analysis: A survey and a new dataset, the STS-Gold. In Proceedings of the 1st Interantional Workshop on Emotion and Sentiment in Social and Expressive Media: Approaches and Perspectives from AI (ESSEM 2013), Turin, Italy, 3 December 2013. [ Google Scholar ]
• Wilson, T.; Wiebe, J.; Hoffmann, P. Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis. Comput. Linguist. 2009 , 35 , 399–433. [ Google Scholar ] [ CrossRef ]
• Agarwal, A.; Xie, B.; Vovsha, I.; Rambow, O.; Passonneau, R.J. Sentiment analysis of twitter data. In Proceedings of the Workshop on Language in Social Media (LSM 2011), Portland, OR, USA, 23 June 2011; pp. 30–38. [ Google Scholar ]
• Wilson, T.; Wiebe, J.; Hoffmann, P. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Vancouver, BC, Canada, 6–8 October 2005; pp. 347–354. [ Google Scholar ]
• Socher, R.; Lin, C.C.Y.; Ng, A.Y.; Manning, C.D. Parsing natural scenes and natural language with recursive neural networks. In Proceedings of the ICML, Bellevue, WA, USA, 28 June–2 July 2011. [ Google Scholar ]
• Wan, X. Co-training for cross-lingual sentiment classification. In Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Singapore, 2–7 August 2009; Su, K., Su, J., Wiebe, J., Eds.; Association for Computational Linguistics: Stroudsburg, PA, USA, 2009; pp. 235–243. [ Google Scholar ]
• Banea, C.; Mihalcea, R.; Wiebe, J.; Hassan, S. Multilingual subjectivity analysis using machine translation. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, Honolulu, HI, USA, 25–27 October 2008; pp. 127–135. [ Google Scholar ]
• Balahur, A.; Turchi, M. Multilingual sentiment analysis using machine translation? In Proceedings of the 3rd Workshop in Computational Approaches to Subjectivity and Sentiment Analysis, Jeju, Republic of Korea, 12 July 2012; pp. 52–60. [ Google Scholar ]
• A.R., B.; Joshi, A.; Bhattacharyya, P. Cross-Lingual Sentiment Analysis for Indian Languages using Linked WordNets. In Proceedings of the COLING 2012: Posters, Mumbai, India, 8–15 December 2012; pp. 73–82. [ Google Scholar ]
• Radford, A.; Wu, J.; Child, R.; Luan, D.; Amodei, D.; Sutskever, I. Language models are unsupervised multitask learners. OpenAI Blog 2019 , 1 , 9. [ Google Scholar ]
• Peters, M.E.; Neumann, M.; Iyyer, M.; Gardner, M.; Clark, C.; Lee, K.; Zettlemoyer, L. Deep contextualized word representations. In Proceedings of the NAACL-HLT, New Orleans, LA, USA, 1–6 June 2018; pp. 2227–2237. [ Google Scholar ]
• Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA, 2–7 June 2019; pp. 4171–4186. [ Google Scholar ] [ CrossRef ]
• Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; Levy, O.; Lewis, M.; Zettlemoyer, L.; Stoyanov, V. Roberta: A robustly optimized bert pretraining approach. arXiv 2019 , arXiv:1907.11692. [ Google Scholar ]
• Grancharova, M.; Dalianis, H. Applying and Sharing pre-trained BERT-models for Named Entity Recognition and Classification in Swedish Electronic Patient Records. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), Reykjavik, Iceland, 31 May–2 June 2021; pp. 231–239. [ Google Scholar ]
• Wang, Z.; Ng, P.; Ma, X.; Nallapati, R.; Xiang, B. Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 3–7 November 2019; pp. 5878–5882. [ Google Scholar ] [ CrossRef ]
• Yang, Z.; Dai, Z.; Yang, Y.; Carbonell, J.; Salakhutdinov, R.R.; Le, Q.V. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Advances in Neural Information Processing Systems, Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 8–14 December 2019 ; Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2019; Volume 32. [ Google Scholar ]
• Jiang, H.; He, P.; Chen, W.; Liu, X.; Gao, J.; Zhao, T. SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 6–8 July 2020; pp. 2177–2190. [ Google Scholar ] [ CrossRef ]
• Das, A.; Sarkar, S. A survey of the model transfer approaches to cross-lingual dependency parsing. ACM Trans. Asian Low-Resour. Lang. Inf. Process. (TALLIP) 2020 , 19 , 67. [ Google Scholar ] [ CrossRef ]
• Chen, X.; Awadallah, A.H.; Hassan, H.; Wang, W.; Cardie, C. Multi-Source Cross-Lingual Model Transfer: Learning What to Share. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28 July–2 August 2019; pp. 3098–3112. [ Google Scholar ] [ CrossRef ]
• Kandula, H.; Min, B. Improving Cross-Lingual Sentiment Analysis via Conditional Language Adversarial Nets. In Proceedings of the Third Workshop on Computational Typology and Multilingual NLP, Online, 10 June 2021; pp. 32–37. [ Google Scholar ] [ CrossRef ]
• Pintu Lohar, M.P.; Way, A. Building English-to-Serbian Machine Translation System for IMDb Movie Reviews. In Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing BSNLP 2019, Florence, Italy, 2 August 2019; pp. 105–113. [ Google Scholar ]
• Chen, X.; Sun, Y.; Athiwaratkun, B.; Cardie, C.; Weinberger, K. Adversarial deep averaging networks for cross-lingual sentiment classification. Trans. Assoc. Comput. Linguist. 2018 , 6 , 557–570. [ Google Scholar ] [ CrossRef ]
• Crystal, D. A Dictionary of Linguistics and Phonetics ; John Wiley & Sons: Hoboken, NJ, USA, 2011. [ Google Scholar ]
• Sussex, R.; Cubberley, P. The Slavic Languages ; Cambridge University Press: Cambridge, UK, 2006. [ Google Scholar ]
• Golubović, J.; Gooskens, C. Mutual Intelligibility between West and South Slavic Languages. Russ. Linguist. 2015 , 39 , 351–373. [ Google Scholar ] [ CrossRef ]
• Townsend, C.E.; Janda, L.A. Common and Comparative Slavic: Phonology and Inflection: With Special Attention to Russian, Polish, Czech, Serbo-Croatian, Bulgarian ; Slavica Pub: Bloomington, IN, USA, 1996. [ Google Scholar ]
• Turney, P. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA, 7–12 July 2002; pp. 417–424. [ Google Scholar ] [ CrossRef ]
• Kim, S.M.; Hovy, E. Determining the sentiment of opinions. In Proceedings of the COLING 2004: 20th International Conference on Computational Linguistics, Genewa, Switzerland, 23–27 August 2004; pp. 1367–1373. [ Google Scholar ]
• Polanyi, L.; Zaenen, A. Contextual valence shifters. In Computing Attitude and Affect in Text: Theory and Applications ; Springer: Berlin/Heidelberg, Germany, 2006; pp. 1–10. [ Google Scholar ]
• Riloff, E.; Wiebe, J. Learning extraction patterns for subjective expressions. In Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, Sapporo, Japan, 11–12 July 2003; pp. 105–112. [ Google Scholar ]
• Esuli, A.; Sebastiani, F. SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy, 22–28 May 2006. [ Google Scholar ]
• Stone, P.J.; Hunt, E.B. A computer approach to content analysis: Studies using the general inquirer system. In Proceedings of the Spring Joint Computer Conference, Detroit, MI, USA, 21–23 May 1963; pp. 241–256. [ Google Scholar ]
• Cambria, E.; Speer, R.; Havasi, C.; Hussain, A. Senticnet: A publicly available semantic resource for opinion mining. In Proceedings of the 2010 AAAI Fall Symposium Series, Arlington, VA, USA, 11–13 November 2010. [ Google Scholar ]
• Nielsen, F.Å. A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. In Proceedings of the Workshop on ‘Making Sense of Microposts’: Big Things Come in Small Packages, Heraklion, Crete, Greece, 30 May 2011; pp. 93–98. [ Google Scholar ]
• Mullen, T.; Collier, N. Sentiment analysis using support vector machines with diverse information sources. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain, 25–26 July 2004; pp. 412–418. [ Google Scholar ]
• McDonald, R.; Hannan, K.; Neylon, T.; Wells, M.; Reynar, J. Structured Models for Fine-to-Coarse Sentiment Analysis. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech Republic, 25–27 June 2007; pp. 432–439. [ Google Scholar ]
• Paulus, R.; Socher, R.; Manning, C.D. Global Belief Recursive Neural Networks. In Advances in Neural Information Processing Systems, Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, QC, Canada, 8–13 December 2014 ; Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K.Q., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2014; Volume 27. [ Google Scholar ]
• Read, J.; Carroll, J. Weakly Supervised Techniques for Domain-Independent Sentiment Classification. In Proceedings of the 1st International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion (TSA ’09), New York, NY, USA, 6 November 2009; pp. 45–52. [ Google Scholar ] [ CrossRef ]
• Moraes, R.; Valiati, J.a.F.; GaviãO Neto, W.P. Document-Level Sentiment Classification: An Empirical Comparison between SVM and ANN. Expert Syst. Appl. 2013 , 40 , 621–633. [ Google Scholar ] [ CrossRef ]
• Huang, E.H.; Socher, R.; Manning, C.D.; Ng, A.Y. Improving word representations via global context and multiple word prototypes. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jeju Island, Republic of Korea, 8–14 July 2012; pp. 873–882. [ Google Scholar ]
• Socher, R.; Huval, B.; Manning, C.D.; Ng, A.Y. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Jeju Island, Republic of Korea, 8–14 July 2012; pp. 1201–1211. [ Google Scholar ]
• Socher, R.; Perelygin, A.; Wu, J.; Chuang, J.; Manning, C.D.; Ng, A.Y.; Potts, C. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA, 18–21 October 2013; pp. 1631–1642. [ Google Scholar ]
• Kalchbrenner, N.; Grefenstette, E.; Blunsom, P. A Convolutional Neural Network for Modelling Sentences. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Baltimore, MD, USA, 22–27 June 2014; pp. 655–665. [ Google Scholar ] [ CrossRef ]
• Kim, Y. Convolutional Neural Networks for Sentence Classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25–29 October 2014; pp. 1746–1751. [ Google Scholar ] [ CrossRef ]
• Wang, X.; Liu, Y.; Sun, C.; Wang, B.; Wang, X. Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China, 26–31 July 2015; pp. 1343–1353. [ Google Scholar ] [ CrossRef ]
• Dong, L.; Wei, F.; Tan, C.; Tang, D.; Zhou, M.; Xu, K. Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Baltimore, MD, USA, 22–27 June 2014; pp. 49–54. [ Google Scholar ] [ CrossRef ]
• Wang, J.; Yu, L.C.; Lai, K.R.; Zhang, X. Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Berlin, Germany, 7–12 August 2016; pp. 225–230. [ Google Scholar ] [ CrossRef ]
• Wang, X.; Jiang, W.; Luo, Z. Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts. In Proceedings of the Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Osaka, Japan, 11–16 December 2016; pp. 2428–2437. [ Google Scholar ]
• Kapukaranov, B.; Nakov, P. Fine-grained sentiment analysis for movie reviews in Bulgarian. In Proceedings of the International Conference Recent Advances in Natural Language Processing, Hissar, Bulgaria, 7–9 September 2015; pp. 266–274. [ Google Scholar ]
• Georgieva-Trifonova, T.; Stefanova, M.; Kalchev, S. Customer Feedback Text Analysis for Online Stores Reviews in Bulgarian. IAENG Int. J. Comput. Sci. 2018 , 45 , 560–568. [ Google Scholar ]
• Lazarova, G.; Koychev, I. Semi-supervised multi-view sentiment analysis. In Computational Collective Intelligence ; Springer: Berlin/Heidelberg, Germany, 2015; pp. 181–190. [ Google Scholar ]
• Osenova, P.; Simov, K.I. The Political Speech Corpus of Bulgarian. In Proceedings of the LREC, Online, 21–27 May 2012; pp. 1744–1747. [ Google Scholar ]
• Smailović, J.; Kranjc, J.; Grčar, M.; Žnidaršič, M.; Mozetič, I. Monitoring the Twitter sentiment during the Bulgarian elections. In Proceedings of the 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Paris, France, 19–21 October 2015; pp. 1–10. [ Google Scholar ]
• Hristova, G. Text Analytics in Bulgarian: An Overview and Future Directions. Cybern. Inf. Technol. 2021 , 21 , 3–23. [ Google Scholar ] [ CrossRef ]
• Steinberger, J.; Ebrahim, M.; Ehrmann, M.; Hurriyetoglu, A.; Kabadjov, M.; Lenkova, P.; Steinberger, R.; Tanev, H.; Vázquez, S.; Zavarella, V. Creating sentiment dictionaries via triangulation. Decis. Support Syst. 2012 , 53 , 689–694. [ Google Scholar ] [ CrossRef ]
• Veselovská, K. Sentence-level sentiment analysis in czech. In Proceedings of the 2nd International Conference on Web Intelligence, Mining and Semantics, Craiova, Romania, 13–15 June 2012; pp. 1–4. [ Google Scholar ]
• Habernal, I.; Brychcín, T. Semantic spaces for sentiment analysis. In Proceedings of the International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, 1–5 September 2013; pp. 484–491. [ Google Scholar ]
• Çano, E.; Bojar, O. Sentiment Analysis of Czech Texts: An Algorithmic Survey. In Proceedings of the 11th International Conference on Agents and Artificial Intelligence, Prague, Czech Republic, 19–21 February 2019; Rocha, A.P., Steels, L., van den Herik, H.J., Eds.; SciTePress: Setúbal, Portugal, 2019; pp. 973–979. [ Google Scholar ] [ CrossRef ]
• Klouda, I.K.; Langr, L.; Ing, D.V. Product Review Sentiment Analysis in the Czech Language Student. Bachelor’s Thesis, Czech Technical University in Prague, Prague, Czech Republic, 2019. [ Google Scholar ]
• Sido, J.; Prazák, O.; Pribán, P.; Pasek, J.; Seják, M.; Konopík, M. Czert—Czech BERT-like Model for Language Representation. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), Online, 1–3 September 2021; Angelova, G., Kunilovskaya, M., Mitkov, R., Nikolova-Koleva, I., Eds.; INCOMA Ltd.: Hyderabad, India, 2021; pp. 1326–1338. [ Google Scholar ]
• Straka, M.; Náplava, J.; Straková, J.; Samuel, D. RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model. arXiv 2021 , arXiv:2105.11314. [ Google Scholar ]
• Vysušilová, P.; Straka, M. Sentiment Analysis (Czech Model). LINDAT/CLARIAH-CZ Digital Library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University. 2021. Available online: http://hdl.handle.net/11234/1-4601 (accessed on 23 April 2023).
• Agić, Ž.; Ljubešić, N.; Tadić, M. Towards sentiment analysis of financial texts in croatian. Bull Mark. 2010 , 143 , 69. [ Google Scholar ]
• Agic, Z.; Merkler, D. Rule-Based Sentiment Analysis in Narrow Domain: Detecting Sentiment in Daily Horoscopes Using Sentiscope. In Proceedings of the 2nd Workshop on Sentiment Analysis Where AI Meets Psychology, Mumbai, India, 15 December 2012; pp. 115–124. [ Google Scholar ]
• Jakopović, H.; Mikelić Preradović, N. Identifikacija Online Imidža Organizacija Temeljem Analize Sentimenata Korisnički Generiranog Sadržaja na Hrvatskim Portalima. Med. Istraž. 2016 , 22 , 63–82. [ Google Scholar ] [ CrossRef ]
• Glavaš, G.; Korenčić, D.; Šnajder, J. Aspect-oriented opinion mining from user reviews in Croatian. In Proceedings of the 4th Biennial International Workshop on Balto-Slavic Natural Language Processing, Sofia, Bulgaria, 8–9 August 2013; pp. 18–23. [ Google Scholar ]
• Mozetič, I.; Grčar, M.; Smailović, J. Multilingual Twitter sentiment classification: The role of human annotators. PLoS ONE 2016 , 11 , e0155036. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Rotim, L.; Šnajder, J. Comparison of short-text sentiment analysis methods for croatian. In Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing, Valencia, Spain, 4 April 2017; pp. 69–75. [ Google Scholar ]
• Robnik-Šikonja, M.; Reba, K.; Mozetič, I. Cross-lingual transfer of sentiment classifiers. Slovenščina 2.0: Empirical. Appl. Interdiscip. Res. 2021 , 9 , 1–25. [ Google Scholar ] [ CrossRef ]
• Lula, P.; Wójcik, K. Sentiment analysis of consumer opinions written in Polish. Econ. Manag. 2011 , 16 , 1286–1291. [ Google Scholar ]
• Haniewicz, K.; Rutkowski, W.; Adamczyk, M.; Kaczmarek, M. Towards the lexicon-based sentiment analysis of polish texts: Polarity lexicon. In Proceedings of the International Conference on Computational Collective Intelligence, Craiova, Romania, 11–13 September 2013; pp. 286–295. [ Google Scholar ]
• Rybiński, K. Political sentiment analysis of press freedom. Stud. Medioznawcze 2018 , 2018 , 31–48. [ Google Scholar ] [ CrossRef ]
• Zaśko-Zielińska, M.; Piasecki, M.; Szpakowicz, S. A large wordnet-based sentiment lexicon for Polish. In Proceedings of the International Conference Recent Advances in Natural Language Processing, Hissar, Bulgaria, 7–9 September 2015; pp. 721–730. [ Google Scholar ]
• Bartusiak, R.; Augustyniak, L.; Kajdanowicz, T.; Kazienko, P. Sentiment Analysis for Polish Using Transfer Learning Approach. In Proceedings of the 2015 Second European Network Intelligence Conference, Karlskrona, Sweden, 21–22 September 2015; pp. 53–59. [ Google Scholar ] [ CrossRef ]
• Kocoń, J.; Zaśko-Zielińska, M.; Miłkowski, P. Multi-level analysis and recognition of the text sentiment on the example of consumer opinions. In Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP 2019), Varna, Bulgaria, 2–4 September 2019. [ Google Scholar ]
• Wawer, A.; Sobiczewska, J. Predicting Sentiment of Polish Language Short Texts. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), Varna, Bulgaria, 2–4 September 2019; pp. 1321–1327. [ Google Scholar ]
• Kuznetsova, E.S.; Loukachevitch, N.V.; Chetviorkin, I.I. Testing rules for a sentiment analysis system. In Proceedings of the Proceedings of International Conference Dialog, Metz, France, 22–24 August 2013; Volume 2, pp. 71–80. [ Google Scholar ]
• Chetviorkin, I.; Loukachevitch, N.V. Evaluating Sentiment Analysis Systems in Russian. In Proceedings of the 4th Biennial International Workshop on Balto-Slavic Natural Language Processing, BSNLP@ACL 2013, Sofia, Bulgaria, 8–9 August 2013; Piskorski, J., Pivovarova, L., Tanev, H., Yangarber, R., Eds.; Association for Computational Linguistics: Stroudsburg, PA, USA, 2013; pp. 12–17. [ Google Scholar ]
• Golubev, A.; Loukachevitch, N.V. Improving Results on Russian Sentiment Datasets. arXiv 2020 , arXiv:2007.14310. [ Google Scholar ]
• Golubev, A.; Loukachevitch, N.V. Transfer Learning for Improving Results on Russian Sentiment Datasets. arXiv 2021 , arXiv:2107.02499. [ Google Scholar ]
• Smetanin, S.; Komarov, M. Deep transfer learning baselines for sentiment analysis in Russian. Inf. Process. Manag. 2021 , 58 , 102484. [ Google Scholar ] [ CrossRef ]
• Machová, K.; Mikula, M.; Gao, X.; Mach, M. Lexicon-based Sentiment Analysis Using the Particle Swarm Optimization. Electronics 2020 , 9 , 1317. [ Google Scholar ] [ CrossRef ]
• Bučar, J.; Povh, J.; Žnidaršič, M. Sentiment classification of the Slovenian news texts. In Proceedings of the 9th International Conference on Computer Recognition Systems CORES, Wroclaw, Poland, 25–27 May 2015; Springer: Berlin/Heidelberg, Germany, 2016; pp. 777–787. [ Google Scholar ]
• Bučar, J. Manually Sentiment Annotated Slovenian News Corpus SentiNews 1.0. Slovenian Language Resource Repository CLARIN.SI. 2017. Available online: http://hdl.handle.net/11356/1110 (accessed on 23 April 2023).
• Žitnik, S. Slovene Corpus for Aspect-Based Sentiment Analysis—SentiCoref 1.0. Slovenian Language Resource Repository CLARIN.SI. 2019. Available online: https://www.clarin.si/repository/xmlui/handle/11356/1285 (accessed on 21 April 2023).
• Pelicon, A.; Pranjić, M.; Miljković, D.; Škrlj, B.; Pollak, S. Sentiment Annotated Dataset of Croatian News. Slovenian Language Resource Repository CLARIN.SI. 2020. Available online: https://www.clarin.si/repository/xmlui/handle/11356/1342 (accessed on 20 April 2023).
• Pelicon, A.; Pranjic, M.; Miljković, D.; Škrlj, B.; Pollak, S. Zero-Shot Learning for Cross-Lingual News Sentiment Classification. Appl. Sci. 2020 , 10 , 5993. [ Google Scholar ] [ CrossRef ]
• Kadunc, K.; Robnik-Šikonja, M. Opinion corpus of Slovene Web Commentaries KKS 1.001. Slovenian Language Resource Repository CLARIN.SI. 2017. Available online: https://www.clarin.si/repository/xmlui/handle/11356/1115 (accessed on 20 April 2023).
• Ljubešić, N.; Fišer, D.; Erjavec, T.; Šulc, A. Offensive language dataset of Croatian, English and Slovenian comments FRENK 1.1. Slovenian Language Resource Repository CLARIN.SI. 2021. Available online: https://www.clarin.si/repository/xmlui/handle/11356/1462 (accessed on 20 April 2023).
• Evkoski, B.; Pelicon, A.; Mozetič, I.; Ljubešić, N.; Kralj Novak, P. Slovenian Twitter Dataset 2018–2020 1.0. Slovenian language resource repository CLARIN.SI. 2021. Available online: https://www.clarin.si/repository/xmlui/handle/11356/1423 (accessed on 20 April 2023).
• Cotterell, R.; Heigold, G. Cross-lingual Character-Level Neural Morphological Tagging. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9–11 September 2017; Palmer, M., Hwa, R., Riedel, S., Eds.; Association for Computational Linguistics: Stroudsburg, PA, USA, 2017; pp. 748–759. [ Google Scholar ] [ CrossRef ]
• Lin, Y.; Chen, C.; Lee, J.; Li, Z.; Zhang, Y.; Xia, M.; Rijhwani, S.; He, J.; Zhang, Z.; Ma, X.; et al. Choosing Transfer Languages for Cross-Lingual Learning. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 28 July–2 August 2019; Korhonen, A., Traum, D.R., Màrquez, L., Eds.; Association for Computational Linguistics: Stroudsburg, PA, USA, 2019; Volume 1: Long Papers, pp. 3125–3135. [ Google Scholar ] [ CrossRef ]
• Mihalcea, R.; Banea, C.; Wiebe, J. Learning Multilingual Subjective Language via Cross-Lingual Projections. In Proceedings of the ACL 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, Prague, Czech Republic, 23–30 June 2007; Carroll, J.A., van den Bosch, A., Zaenen, A., Eds.; The Association for Computational Linguistics: Stroudsburg, PA, USA, 2007. [ Google Scholar ]
• Feng, Y.; Wan, X. Towards a unified end-to-end approach for fully unsupervised cross-lingual sentiment analysis. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Hong Kong, China, 3–4 November 2019; pp. 1035–1044. [ Google Scholar ]
• Kanayama, H.; Nasukawa, T.; Watanabe, H. Deeper Sentiment Analysis Using Machine Translation Technology. In Proceedings of the COLING 2004: 20th International Conference on Computational Linguistics, Geneva, Switzerland, 23–27 August 2004; pp. 494–500. [ Google Scholar ]
• Galeshchuk, S.; Qiu, J.; Jourdan, J. Sentiment Analysis for Multilingual Corpora. In Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, BSNLP@ACL 2019, Florence, Italy, 2 August 2019; Erjavec, T., Marcinczuk, M., Nakov, P., Piskorski, J., Pivovarova, L., Snajder, J., Steinberger, J., Yangarber, R., Eds.; Association for Computational Linguistics: Stroudsburg, PA, USA, 2019; pp. 120–125. [ Google Scholar ] [ CrossRef ]
• Lohar, P.; Afli, H.; Way, A. Maintaining Sentiment Polarity of Translated User Generated Content. Prague Bull. Math. Linguist. 2017 , 108 , 73–84. [ Google Scholar ] [ CrossRef ]
• Lohar, P.; Afli, H.; Way, A. Balancing Translation Quality and Sentiment Preservation. In Proceedings of the 13th Conference of the Association for Machine Translation in the Americas, Boston, MA, USA, 17–21 March 2018; pp. 81–88. [ Google Scholar ]
• Vulic, I.; Moens, M. Cross-Lingual Semantic Similarity of Words as the Similarity of Their Semantic Word Responses. In Proceedings of the 2013 Conference of the North American Chapter of the Association of Computational Linguistics: Human Language Technologies, Atlanta, GA, USA, 9–14 June 2013; Vanderwende, L., Daumé, H., III, Kirchhoff, K., Eds.; The Association for Computational Linguistics: Stroudsburg, PA, USA, 2013; pp. 106–116. [ Google Scholar ]
• Conneau, A.; Wu, S.; Li, H.; Zettlemoyer, L.; Stoyanov, V. Emerging Cross-lingual Structure in Pretrained Language Models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5–10 July 2020; Jurafsky, D., Chai, J., Schluter, N., Tetreault, J.R., Eds.; Association for Computational Linguistics: Stroudsburg, PA, USA, 2020; pp. 6022–6034. [ Google Scholar ] [ CrossRef ]
• Li, Z.; Zhang, Y.; Wei, Y.; Wu, Y.; Yang, Q. End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, 19–25 August 2017; Sierra, C., Ed.; AAAI Press: Washington, DC, USA, 2017; pp. 2237–2243. [ Google Scholar ] [ CrossRef ]
• Long, M.; CAO, Z.; Wang, J.; Jordan, M.I. Conditional Adversarial Domain Adaptation. In Advances in Neural Information Processing Systems, Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, QC, Canada, 3–8 December 2018 ; Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2018; Volume 31. [ Google Scholar ]
• Fei, H.; Li, P. Cross-lingual unsupervised sentiment classification with multi-view transfer learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 5–10 July 2020; pp. 5759–5771. [ Google Scholar ]
• Dong, D.; Wu, H.; He, W.; Yu, D.; Wang, H. Multi-task learning for multiple language translation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China, 26–31 July 2015; pp. 1723–1732. [ Google Scholar ]
• Johnson, M.; Schuster, M.; Le, Q.V.; Krikun, M.; Wu, Y.; Chen, Z.; Thorat, N.; Viégas, F.; Wattenberg, M.; Corrado, G.; et al. Google’s multilingual neural machine translation system: Enabling zero-shot translation. Trans. Assoc. Comput. Linguist. 2017 , 5 , 339–351. [ Google Scholar ] [ CrossRef ]
• Habernal, I.; Ptáček, T.; Steinberger, J. Sentiment analysis in czech social media using supervised machine learning. In Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Atlanta, GA, USA, 14 June 2013; pp. 65–74. [ Google Scholar ]
• Pang, B.; Lee, L.; Vaithyanathan, S. Thumbs up? Sentiment Classification using Machine Learning Techniques. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), Philadelphia, PA, USA, 6–7 July 2002; Association for Computational Linguistics: Stroudsburg, PA, USA, 2002; pp. 79–86. [ Google Scholar ] [ CrossRef ]
• Keung, P.; Lu, Y.; Szarvas, G.; Smith, N.A. The Multilingual Amazon Reviews Corpus. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online, 16–20 November 2020; pp. 4563–4568. [ Google Scholar ] [ CrossRef ]
• Pecar, S.; Simko, M.; Bielikova, M. Improving Sentiment Classification in Slovak Language. In Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, Florence, Italy, 29 June 2019; Association for Computational Linguistics: Stroudsburg, PA, USA, 2019. [ Google Scholar ]
• McDonald, R.; Petrov, S.; Hall, K. Multi-Source Transfer of Delexicalized Dependency Parsers. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, UK, 27–31 July 2011; pp. 62–72. [ Google Scholar ]
• Thongtan, T.; Phienthrakul, T. Sentiment Classification Using Document Embeddings Trained with Cosine Similarity. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, Florence, Italy, 28 July–2 August 2019; pp. 407–414. [ Google Scholar ] [ CrossRef ]
• Wolf, T.; Debut, L.; Sanh, V.; Chaumond, J.; Delangue, C.; Moi, A.; Cistac, P.; Rault, T.; Louf, R.; Funtowicz, M.; et al. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online, 16–20 November 2020; pp. 38–45. [ Google Scholar ] [ CrossRef ]
• Wu, Z.; Saito, S. HiNet: Hierarchical Classification with Neural Network. arXiv 2017 , arXiv:1705.11105. [ Google Scholar ]
• Thakkar, G.; Preradovic, N.M.; Tadic, M. Multi-task Learning for Cross-Lingual Sentiment Analysis. In Proceedings of the 2nd International Workshop on Cross-Lingual Event-Centric Open Analytics Co-Located with the 30th The Web Conference (WWW 2021), Ljubljana, Slovenia, 12 April 2021; Demidova, E., Hakimov, S., Winters, J., Tadic, M., Eds.; Sun SITE Central Europe: Aachen, Germany, 2021; Volume 2829, CEUR Workshop Proceedings. pp. 76–84. [ Google Scholar ]
• Collobert, R.; Weston, J.; Bottou, L.; Karlen, M.; Kavukcuoglu, K.; Kuksa, P.P. Natural Language Processing (Almost) from Scratch. J. Mach. Learn. Res. 2011 , 12 , 2493–2537. [ Google Scholar ]
• Dror, R.; Shlomov, S.; Reichart, R. Deep Dominance—How to Properly Compare Deep Neural Models. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28 July–2 August 2019; Korhonen, A., Traum, D., Màrquez, L., Eds.; pp. 2773–2785. [ Google Scholar ] [ CrossRef ]
• Ulmer, D.; Hardmeier, C.; Frellsen, J. deep-significance-Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks. arXiv 2022 , arXiv:2204.06815. [ Google Scholar ]
• Del Barrio, E.; Cuesta-Albertos, J.A.; Matrán, C. An optimal transportation approach for assessing almost stochastic order. In The Mathematics of the Uncertain ; Springer: Berlin/Heidelberg, Germany, 2018; pp. 33–44. [ Google Scholar ]
• Yeh, A. More accurate tests for the statistical significance of result differences. In Proceedings of the COLING 2000 Volume 2: The 18th International Conference on Computational Linguistics, Saarbrücken, Germany, 31 July–4 August 2000. [ Google Scholar ]
• Přibáň, P.; Steinberger, J. Are the Multilingual Models Better? Improving Czech Sentiment with Transformers. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), Online, 1–3 September 2021; pp. 1138–1149. [ Google Scholar ]
• Pikuliak, M.; Grivalský, Š.; Konôpka, M.; Blšták, M.; Tamajka, M.; Bachratý, V.; Simko, M.; Balážik, P.; Trnka, M.; Uhlárik, F. SlovakBERT: Slovak Masked Language Model. In Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, 7–11 December 2022; Goldberg, Y., Kozareva, Z., Zhang, Y., Eds.; pp. 7156–7168. [ Google Scholar ] [ CrossRef ]
• Přibáň, P.; Šmíd, J.; Steinberger, J.; Mištera, A. A comparative study of cross-lingual sentiment analysis. Expert Syst. Appl. 2024 , 247 , 123247. [ Google Scholar ] [ CrossRef ]

Click here to enlarge figure

Share and Cite

Thakkar, G.; Preradović, N.M.; Tadić, M. Transferring Sentiment Cross-Lingually within and across Same-Family Languages. Appl. Sci. 2024 , 14 , 5652. https://doi.org/10.3390/app14135652

Thakkar G, Preradović NM, Tadić M. Transferring Sentiment Cross-Lingually within and across Same-Family Languages. Applied Sciences . 2024; 14(13):5652. https://doi.org/10.3390/app14135652

Thakkar, Gaurish, Nives Mikelić Preradović, and Marko Tadić. 2024. "Transferring Sentiment Cross-Lingually within and across Same-Family Languages" Applied Sciences 14, no. 13: 5652. https://doi.org/10.3390/app14135652

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

Shopify: Valuation Does Not Match Fundamentals

• Shopify's fundamentals are quite strong, with impressive revenue growth, operating leverage, and a fortress balance sheet.
• However, even considering all the company's fundamental strengths and growth potential, the current valuation is too generous, with a 44% premium over the fair value.
• Moreover, Wall Street analysts' sentiment regarding the upcoming Q2 earnings release is quite bearish, with more than twenty downward EPS revisions.

Investment thesis

My previous cautious thesis about Shopify ( NYSE: SHOP ) aged well, as the stock is significantly underperforming compared to the broader market since November 2023. More than six months passed since my previous coverage and today I want to share my updated analysis of Shopify.

Shopify remains fundamentally robust with strong revenue growth momentum, operating leverage, and a fortress balance sheet. The management works hard on improving the ecosystem, which is another long-term bullish sign. However, my discounted cash flow analysis suggests that the stock is massively overvalued. Moreover, the recent history of Q2 consensus EPS downgrades suggests that the Wall Street sentiment is quite pessimistic. All in all, I reiterate my "Hold" rating for SHOP.

Recent developments

The latest quarterly earnings were released on May 8, when the company surpassed consensus estimates. Revenue grew by 23.4% YoY. The adjusted EPS expanded significantly, from $0.01 to $0.20.

Seeking Alpha

The EPS expansion was of high quality as the operating margin expanded from -10% to 7.4% YoY. On the other hand, a major part of expansion was achieved after cutting the R&D to revenue ratio from 30% to sub-18%. The free cash flow [FCF] less stock-based compensation [SBC] was quite modest at around $66. Nevertheless, it contributed to the company's balance sheet which is a fortress with $5 billion cash pile and much lower total debt levels.

The upcoming earnings release is scheduled for July 26. The adjusted EPS is expected to remain flat sequentially despite a projected 8% QoQ revenue growth. On a YoY basis, revenue is expected to grow around 19%, and the adjusted EPS to expand from $0.14 to $0.20. Wall Street sentiment around the upcoming earnings release is quite pessimistic with 23 EPS downgrades over the last 90 days, which is a bearish sign.

The management continues working hard on improving Shopify's ecosystem. We see it from aggressive R&D spending, which is still high in absolute terms despite a YoY contraction in the R&D to revenue ratio. Apart from in-house developments, Shopify also expands its partnerships network. The recent partnership expansion with Avalara will help merchants to streamline their processes related to tax compliance.

Amid the current AI revolution Shopify also does not forget about these cutting-edge technologies. The company recently expanded access to its AI-powered tools, which will also highly likely add the appeal of its ecosystem. Features include the Sidekick assistant and image-generation tools, which will also help merchants in streamlining their operations.

On the other hand, the macro environment remains quite uncertain. The Fed is still not cutting rates and now the market expects only one cut in 2024, instead of three cuts which were expected just a few months ago. Moreover, I think that there is a real probability of the Fed not cutting rates at all in 2024. I think so because there are really no reasons to rush as the U.S. economy is still robust, the unemployment rate is still close historical lows, and the fight against inflation looks over. The Fed highly likely realizes that easing monetary policy can lead to a spike in energy prices, which can launch a new wave of inflation growth. Therefore, from the macro environment perspective, the stock's near-term prospects look quite cloudy.

Valuation update

The stock was almost flat over the last twelve months with a modest 2.6% price increase. YTD performance looks poor with a 17% share price decrease. Despite the share price plunge, SHOP's valuation ratios are still extremely high. Most of ratios are lower than historical averages, but still around 10 P/S ratio looks too generous, in my opinion.

However, SHOP's valuation ratios might be misleading because the company is aggressively growing. Therefore, I must simulate the discounted cash flow [DCF] model, and I want to start with figuring out the company's cost of equity. I ignore cost of debt for the discount rate because SHOP's debt levels are insignificant compared to its market cap. The discount rate is calculated using the CAPM approach and all variables are easily available on the Internet. According to calculations, SHOP's cost of equity is 17.25%.

Author's calculations

Consensus estimates project an 18% revenue CAGR, which I incorporate into my DCF model. The TTM FCF ex-SBC margin is 2.5%, which is my base year's assumption. I project a 150 basis points yearly expansion for the FCF margin because of the expected solid revenue growth.

My DCF simulation suggests that the business's fair value is around $47 billion, substantially lower than the current market capitalization. That said, the stock is significantly overvalued. I agree that a 17.25% discount rate might be too aggressive for SHOP. However, even with a soft 10% discount rate Shopify's valuation does not look justified.

To conclude, Shopify's valuation looks far from being called attractive. Even with a very soft discount rate and aggressive 18% revenue CAGR, the stock is still overvalued.

Risks to my cautious thesis

Shopify's fundamentals are strong as the company demonstrates solid revenue growth and operating leverage. It has ample liquidity to continue investing loads of money in innovation and marketing, which can help in increasing revenue and EPS faster than consensus estimates project. That said, should SHOP deliver a strong earnings surprise in July, there might be a massive rally.

Moreover, Shopify's performance is historically strong in July. The below bar chart from TrendSpider suggests that over the last nine years, July was positive in almost 90% of cases.

TrendSpider

As we saw in the valuation update, SHOP's beta is extremely high. This means that the stock is volatile, and this includes swings in both directions. The stock has a history of showing sudden spikes in its price, which also might make my thesis look not good.

Bottom line

To conclude, I reiterate my "Hold" rating for SHOP. I think that the valuation is not justified despite all the fundamental strengths of the company. I am not ready to pay such a premium for the company which competes directly with a monster like Amazon ( AMZN ). Moreover, Wall Street analysts' sentiment around July's earnings release is quite pessimistic.

This article was written by

Analyst’s Disclosure: I/we have no stock, option or similar derivative position in any of the companies mentioned, and no plans to initiate any such positions within the next 72 hours. I wrote this article myself, and it expresses my own opinions. I am not receiving compensation for it (other than from Seeking Alpha). I have no business relationship with any company whose stock is mentioned in this article.

Seeking Alpha's Disclosure: Past performance is no guarantee of future results. No recommendation or advice is being given as to whether any investment is suitable for a particular investor. Any views or opinions expressed above may not reflect those of Seeking Alpha as a whole. Seeking Alpha is not a licensed securities dealer, broker or US investment adviser or investment bank. Our analysts are third party authors that include both professional investors and individual investors who may not be licensed or certified by any institute or regulatory body.

Recommended For You

About shop stock.

More on SHOP

Related stocks.

Trending Analysis

Trending news.

2024 Theses Doctoral

Futurity after the End of History: Chronotopes of Contemporary German Literature, Film, and Music

Wagner, Nathaniel Ross

This dissertation deploys theories of spatiotemporal experience and organization, most prominently Mikhail Bakhtin’s “chronotope,” to set contemporary literature, film, and music into dialogue with theories of post-Wende social and political experiences and possibility that speak, with Francis Fukuyama, as the contemporary as the “End of History.” Where these interlocutors of Fukuyama generally affirm or intensify his view of the contemporary as a time where historical progress slows to a halt, historical memory recedes from view, and the conditions of subjecthood are rephrased from participation in a struggle for progress to mindless consumption and technocratic tinkering, I engage contemporary artwork to flesh out and ultimately peer beyond the boundaries of the real and the possible these social theories articulate. Through a series of close readings of German films, music albums, and novels published between 1995 and 2021, I examine how German authors, filmmakers, and musicians pursue depictions of the malaises of the End of History while also resolutely pointing to the fissures in liberal capitalist hegemony where history—its past and its future—again becomes visible. Mikhail Bakhtin’s notion of the chronotope, a text’s unified expression of space and time, is central to my method of analysis. In tracing the chronotopic contours of contemporary works of music, film, and literature, I argue, we—as readers, viewers, and listeners—are engaged to think and act alongside the forms and figures that populate the worlds their authors create. In doing so, we ultimately uncover forceful accusations, resolute alternatives, and even hopeful antidotes to the deficiencies of our present that help us both to soberly contemplate the implications the pessimistic formulations of contemporary theory have on our lives, communities, and futures but also to formulate possibilities for them that lie beyond their analytical purview.In a series of close readings of my literary, filmic, and musical primary texts, I engage theorists of the post-Cold War, post-Wende contemporary who write about the political order and social conditions emerging out of the triumph of neoliberalism and market capitalism over socialist, communist, and fascist alternatives. The dissertation begins by establishing a wide view of the contemporary, tracing in its first chapter chronotopic resonances of Hartmut Rosa’s “social acceleration” thesis—which locates the aimlessness and alienation of contemporary society within the accelerationist logic of market capitalist modes of production—across the full temporal arc of the contemporary. Pairing Christian Kracht’s Faserland (1995) with Fatma Aydemir's Ellbogen (2017), I argue that the futilities and frustrations of the modern subject, as foretold in Fukuyama’s “End of History” essay and fleshed out in Rosa’s writings on social acceleration, find resonance not only in the wealthy, educated, white protagonist of Faserland’s 1990s, but also in the impoverished, undereducated, Turkish-Kurdish protagonist of Ellbogen some twenty years later. What connects these two accounts across decades and differences in identities, I demonstrate, is not merely a shared sense of alienation and despair, but a shared, underlying chronotopic characterization of the contemporary. These commonalities appear, I demonstrate, when we connect Rosa’s “social acceleration” thesis to diegetic chronotopes of perpetual motion that depict modern subjects’ inability to avail themselves of the ostensibly liberatory potential of liberal capitalism’s accelerated lifeworld. Chapter 2 then considers Byung-Chul Han’s theory of auto-exploitation and the dilemma of the music novel at a time where the rebellion of punk against social integration has been thoroughly incorporated into capitalism. Reading Marc Degens’ Fuckin Sushi (2015), I examine the novel’s concept of “Abrentnern” as a model for personal and communal fulfillment for those who turn to art as a means self-determination in the age of auto-exploitation. Unlike Kracht and Aydemir, however, Degens sees the closing off of historical possibilities for the good life enjoyed by his punk forbears—here, self-determination through transgressive artistic praxis—not as the contemporary subject’s damnation to cyclical patterns of despair but as a challenge to conceive of the good life anew. Working humorously through its hapless protagonist Niels’ repeated attempts to escape the seemingly inevitable for-profit co-option of his sincere artistic efforts, the novel serves to unveil the persistence of blind spots in this regime of totalizing exploitation. What results is an account of the double-edged logic of capitalist productivity’s ostensible totalization of labor-time. Capitalism, Niels unwittingly discovers, is a logic of production so overwhelming that it continuously drives subjects towards the discovery of new alterities that, for a brief time at least, allow subjects once again to slip between the cracks. The third chapter explores a similar phenomenon of halting resistance to the conditions of the capitalist present through the lens of futurity. Here, I push back against Mark Fisher’s theory of the dominance of “Capitalist Realism” in the contemporary aesthetic imagination, identifying and developing the notion of “subtle futurity”—the modest, yet resolute rephrasing of future possibility beyond the “way things are” of the present—in Leif Randt’s Schimmernder Dunst über CobyCounty (2011) In this light, I argue, Randt’s gestures towards a different future, however halting, mark a significant effort to imagine a benevolent form of future possibility within the context of an era often suspected to have been exhausted of its utopian sentiment. The final two chapters turn to past-minded works that more forcefully repudiate notions of the present as static or closed off from the movement of history. Chapter Four considers W.G. Sebald’s 1995 novel, Die Ringe des Saturn, and The Caretaker’s 2012 album, Patience (After Sebald), developing an account of the chronotopic means by which these works revisit materials of the past within the present. Chronotopic motifs of paraphrase—techniques of sampling in The Caretaker and narrative polyphony in Sebald—come together within macro-level chronotopic frameworks of peripatetic movement—looping repetition in The Caretaker and the retracing of bygone journeys in Sebald—to testify to the unanswered questions and unfinished work of history over and against notions of the present as a time where the past has been relegated to mere museum content or nostalgia for bygone ways of living. Where Chapter Four speaks primarily to the formal mechanisms by which the present rediscovers the past, Chapter Five examines two specific chronotopic innovations for thematically engaging constellations of past-present inter-temporality. Both Sharon Dodua Otoo’s 2021 novel, Adas Raum, and Christian Petzold’s 2018 film, Transit, develop chronotopes wherein past and present are intermingled in increasingly inseparable ways. Adas Raum, I demonstrate, is organized spatiotemporally as a nexus of coiled loops—pasts and presents intertwine, heaven and earth are tangled together, and the fates of human beings and even non-human objects follow spatial and temporal trajectories that weave in and out of conventional linear understandings of space and time. In similar fashion, past and present become inseparable in Petzold’s film, an adaptation of the Anna Seghers’ 1944 novel of the same name, through thematic and formal approaches of blurring that blend the plight of refugees of Seghers’ era with those of Petzold’s present day. History, then, appears remarkably robust in these texts, unfolding accounts of how human beings living through their present might take guidance from the generations that preceded them in the struggle for a better world.

• Motion pictures, German
• Germans--Music
• Capitalism in literature
• Social integration
• Neoliberalism
• Twenty-first century
• Future, The, in literature
• Sebald, W. G. (Winfried Georg), 1944-2001
• Bakhtin, M. M. (Mikhail Mikhaĭlovich), 1895-1975
• Petzold, Christian, 1960-
• Fukuyama, Francis
• Kracht, Christian, 1966-
• Rosa, Hartmut, 1965-
• Ringe des Saturn (Sebald, W. G.)
• End of history and the last man (Fukuyama, Francis)

This item is currently under embargo. It will be available starting 2029-06-14.

More About This Work

• DOI Copy DOI to clipboard