Conference Paper2019Cited by 20

Analyzing Performance of Different Machine Learning Approaches With Doc2vec for Classifying Sentiment of Bengali Natural Language

Md Tazimul Hoque, Ashraful Islam, Eshtiak Ahmed, Khondaker A Mamun, Mohammad Nurul Huda

2019 International Conference on Electrical, Computer and Communication Engineering (ECCE)

IEEE, pp. 1–5

DOI: 10.1109/ecace.2019.8679272URL

Abstract

Vector or numeric representation of text documents has been a revolution in natural language processing as it represents similar parts of text in such a way that they are very close to each other, making it very easy to classify or find similarities among them. These vectors also represent the way we use the words or parts of documents as well which helps finding similarity even between pair of words. While word2vec is such a technique that represents each word as a vector, doc2vec takes it to another level by representing a whole sentence or document as a vector. Being able to represent an entire document as a vector allows comparing a substantial number of words or sentences at a time which can save computational power as well as bandwidth. This relatively newer doc2vec technology has not yet been implemented for Bengali sentiment analysis and its feasibility is also unknown. In this study, we have trained a doc2vec model using a corpus constructed with 7,000 Bengali sentences. The model consists of two types of data differentiated by their polarity i.e. positive and negative. Later, we have employed several machine learning algorithms for comparing the accuracy of classification among which Bi-Directional Long Short-Term Memory (BLSTM) has obtained the highest accuracy of 77.85% along with precision, recall and F-1 score of 78.06%,77.39% and 77.72% respectively.

Keywords

  • Doc2Vec
  • document vectorization
  • Word2vec
  • bidirectional long short-term memory
  • Bengali language
  • polarity classification

CCDS Authors

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Eshtiak Ahmed
Eshtiak Ahmed

Eshtiak Ahmed

  • Collaborator, HCI Wing

Doctoral Researcher

Gamification Group

Tampere University, Finland

Published at

UbiComp, ICIP, HCII, IEEE Access

Research Interests

Human-Computer Interaction, Human-Robot Interaction, Gamification and Assistive Technologies

References

  1. 1.Bo Pang, Lillian Lee. (2008). Opinion Mining and Sentiment Analysis. now publishers, Inc. eBooks[10.1561/9781601981516]
  2. 2.Bo Pang, Lillian Lee. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends® in Information Retrieval, 2(1-2), 1–135[10.1561/1500000011]
  3. 3.Peter Peter, Turney. (2002). Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Meeting of the Association for Computational Linguistics, 417–424
  4. 4.Theresa Wilson, Janyce Wiebe, Paul Hoffmann. (2005). Recognizing contextual polarity in phrase-level sentiment analysis. , 347–354[10.3115/1220575.1220619]
  5. 5.Kushal Dave, Steve Lawrence, David M. Pennock. (2003). Mining the peanut gallery. , 519[10.1145/775152.775226]
  6. 6.Erik Cambria. (2016). Affective Computing and Sentiment Analysis. IEEE Intelligent Systems, 31(2), 102–107[10.1109/mis.2016.31]
  7. 7.Kushal Dave, Steve Lawrence, David M. Pennock. (2003). Mining the peanut gallery. [10.1145/775224.775226]
  8. 8.Rui Gaspar, Cláudia Pedro, Panos Panagiotopoulos, Beate Seibt. (2015). Beyond positive or negative: Qualitative sentiment analysis of social media reactions to unexpected stressful events. Computers in Human Behavior, 56, 179–191[10.1016/j.chb.2015.11.040]
  9. 9.Xi Ouyang, Pan Zhou, Cheng Hua Li, Lijun Liu. (2015). Sentiment Analysis Using Convolutional Neural Network. , 2359–2364[10.1109/cit/iucc/dasc/picom.2015.349]
  10. 10.Shaika Chowdhury, Wasifa Chowdhury. (2014). Performing sentiment analysis in Bangla microblog posts. , 1–6[10.1109/iciev.2014.6850712]
  11. 11.Amandeep Kaur, Vishal Gupta. (2013). A Survey on Sentiment Analysis and Opinion Mining Techniques. Journal of Emerging Technologies in Web Intelligence, 5(4)[10.4304/jetwi.5.4.367-371]
  12. 12.Asif Hassan, Mohammad Rashedul Amin, Abul Kalam Al Azad, Nabeel Mohammed. (2016). Sentiment analysis on bangla and romanized bangla text using deep recurrent models. , 51–56[10.1109/iwci.2016.7860338]
  13. 13.Md. Al-Amin, Md. Saiful Islam, Shapan Das Uzzal. (2017). Sentiment analysis of Bengali comments with Word2Vec and sentiment information of words. , 186–190[10.1109/ecace.2017.7912903]
  14. 14.Quoc V. Le, Tomáš Mikolov. (2014). Distributed Representations of Sentences and Documents. arXiv (Cornell University), 4, 1188–1196[10.48550/arxiv.1405.4053]
  15. 15.Peter D. Turney. (2002). Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. ArXiv.org[10.48550/arxiv.cs/0212032]
  16. 16.(2003). Proceedings of the 2003 conference on Empirical methods in natural language processing -. [10.3115/1119355]

Cited By

  1. 1.Khushi Kalasampath, K. N. Spoorthi, Sreeparvathy Sajeev, Sahil Sarma Kuppa, Kavya Ajay, Angulakshmi Maruthamuthu. (2025). A Literature Review on Applications of Explainable Artificial Intelligence (XAI). IEEE Access, 13, 41111–41140[10.1109/access.2025.3546681]
  2. 2.Saeed Mian Qaisar. (2020). Sentiment Analysis of IMDb Movie Reviews Using Long Short-Term Memory. , 1–4[10.1109/iccis49240.2020.9257657]
  3. 3.Jose Aguilar, Camilo Salazar, Henry Velasco, Julian Monsalve-Pulido, Edwin Montoya. (2020). Comparison and Evaluation of Different Methods for the Feature Extraction from Educational Contents. Computation, 8(2), 30[10.3390/computation8020030]
  4. 4.Muhammad Usama Islam, Md. Mozaharul Mottalib, Mehedi Hassan, Zubair Ibne Alam, S. M. Zobaed, Md. Fazle Rabby. (2022). The Past, Present, and Prospective Future of XAI: A Comprehensive Review. Studies in computational intelligence, 1–29[10.1007/978-3-030-96630-0_1]
  5. 5.Nasif Alvi, Kamrul Hasan Talukder. (2021). Sentiment Analysis of Bengali Text using CountVectorizer with Logistic Regression. , 01–05[10.1109/icccnt51525.2021.9580017]
  6. 6.Nasif Alvi, Kamrul Hasan Talukder, Abdul Hasib Uddin. (2021). Sentiment Analysis of Bangla Text Using Gated Recurrent Neural Network. Advances in intelligent systems and computing, 77–86[10.1007/978-981-16-2597-8_7]
  7. 7.Nolak Kapali, Tariquzzaman Tuhin, Anik Pramanik, Md. Sadekur Rahman, Sheak Rashed Haider Noori. (2022). Sentiment Analysis of Facebook and YouTube Bengali Comments Using LSTM and Bi-LSTM. 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), 1–6[10.1109/icccnt54827.2022.9984395]
  8. 8.Sabrina Jahan Maisha, Nuren Nafisa, Abdul Kadar Muhammad Masum. (2021). Supervised Machine Learning Algorithms for Sentiment Analysis of Bangla Newspaper. International Journal of Innovative Computing, 11(2), 15–23[10.11113/ijic.v11n2.321]
  9. 9.Shumaiya Akter Shammi, Sajal Das, Narayan Ranjan Chakraborty, Sumit Kumar Banshal, Nishu Nath. (2022). A Comprehensive Roadmap on Bangla Text-based Sentiment Analysis. ACM Transactions on Asian and Low-Resource Language Information Processing, 22(4), 1–29[10.1145/3572783]
  10. 10.Ahmad R Pratama. (2022). Sentiment Analysis of Facebook Posts through Special Reactions: The Case of Learning from Home in Indonesia Amid COVID-19. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 8(1), 83[10.26555/jiteki.v8i1.23615]
  11. 11.Muhammad Asad Manzoor, Saeed-Ul Hassan, Amina Muazzam, Suppawong Tuarob, Raheel Nawaz. (2022). Social mining for sustainable cities: thematic study of gender-based violence coverage in news articles and domestic violence in relation to COVID-19. Journal of Ambient Intelligence and Humanized Computing, 14(11), 14631–14642[10.1007/s12652-021-03401-8]
  12. 12.Shammy Shikder Shanta, Md. Sham-E-Ansari, Atiqul Islam Chowdhury, Mohammad Munem Shahriar, Md. Khairul Hasan. (2021). A Comparative Analysis of Different Approach for Basic Emotions Recognition from Speech. 2021 International Conference on Electronics, Communications and Information Technology (ICECIT), 1–4[10.1109/icecit54077.2021.9641208]
  13. 13.Rim Chaib, Nabiha Azizi, Nawel Zemmal, Didier Schwab, Samir Brahim Belhaouari. (2021). Improved Multi-label Medical Text Classification Using Features Cooperation. Lecture notes on data engineering and communications technologies, 61–71[10.1007/978-3-030-70713-2_7]
  14. 14.Juan Pablo Tessore, Leonardo Martín Esnaola, Laura Lanzarini, Sandra Baldassarri. (2021). Distant Supervised Construction and Evaluation of a Novel Dataset of Emotion-Tagged Social Media Comments in Spanish. Cognitive Computation, 14(1), 407–424[10.1007/s12559-020-09800-x]
  15. 15.Tuhin Hossain, Ahmed Ainun Nahian Kabir, Md. Ahasun Habib Ratul, Abdus Sattar. (2022). Sentence Level Sentiment Classification Using Machine Learning Approach in the Bengali Language. 2022 International Conference on Decision Aid Sciences and Applications (DASA), 10, 1286–1289[10.1109/dasa54658.2022.9765266]
  16. 16.Hossen, Md Imran, Islam, Ashraful, Anowar, Farzana, Ahmed, Eshtiak, Rahman, Mohammad Masudur, Xiali, Hei. (2021). Generating Cyber Threat Intelligence to Discover Potential Security Threats Using Classification and Topic Modeling. arXiv (Cornell University)[10.48550/arxiv.2108.06862]
  17. 17.Thien Ho Huong, Kiet Tran-Trung, Daphne Teck Ching Lai, Vinh Truong Hoang. (2022). Sentiment Analysis based on word vector representation for short comments in Vietnamese language. , 165–169[10.1109/nics56915.2022.10013426]
  18. 18.Obaidul Haque, Ashraful Hossain, Mariha Tabassum, Rajib Khan, Fahim Shakil Tamim. (2025). BanglaBERT-BiLSTM: A Novel Hybrid Architecture for Multiclass Mental Health Classification in Bengali Social Media Text. , 3958–3963[10.1109/iccit68739.2025.11490465]
  19. 19.Syahirunnisaa Mohd Azmi, Nurazian Mior Dahalan, Khyrina Airin Fariza Abu Samah, Nurbaity Sabri. (2025). Sentiment Analysis of Visual, Auditory, and Kinesthetic Learning Styles Using Logistic Regression. , 1–6[10.1109/isiea65768.2025.11138254]
  20. 20.Jui Sur Chaudhury, Raina Paul, Sayani Mondal. (2026). Sentiment Analysis of Bengali Literature Using NLP. Lecture notes in networks and systems, 157–173[10.1007/978-981-96-9239-2_12]
← All publications