Sentiment Analysis (SA) has became a main stream research during the last two decades with a immense possibility. On the other hand the evolution of social media texts – such as blogs, micro-blogs (e.g., Twitter), and chats (e.g., Facebook messages) – has created many new opportunities for information access and language technology, but also many new challenges, making it one of the prime present-day research areas. Indeed sentiment analysis in social media text is a hot research discipline in present days, but most of the efforts so far have been made on English. To this end this shared task: SAIL will patronize Indian researchers to work on automatic sentiment analysis for their own languages by providing them relevant data. Prime motivation of the SAIL 2015 is to gather researchers, experts and practitioners together to discuss, collaborate and instigate the SA research particularly for Indian languages, which involves resource creation, sharing and future collaboration.

The Task

Participants will be provided training, development and test data to report the efficiency of their sentiment analysis system. Hindi, and Bengali annotated tweets will be released. We are also planning to have Tamil and Telugu data. Efficiency will be measured in terms of Precision, Recall, and F-measure. Shortlisted candidates will present their techniques and results in a special session at MIKE 2015.

Run Submission

Each team may submit up to two runs, one constrained and one unconstrained.

Constrained: Means the participant team is only allowed to use our corpus (at most SentiWordNet (ILs), made available) and for the training. No external resource is allowed.

Unconstrained: Means the participant team can use any external resource (POS tagger, NER, Parser, and additional data) to train their system. Accordingly they have to mention those resources explicitly in their task-report. .


  • A. Das and S. Bandyopadhyay. SentiWordNet for Indian Languages, In the 8th Workshop on Asian Language Resources (ALR), COLING 2010, Pages 56-63, August, Beijing, China. pdf
  • A. Das and S. Bandyopadhyay. Dr Sentiment Knows Everything!, In the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL/HLT 2011 Demo Session), Pages 50-55, June, Portland, Oregon, USA. pdf
  • D. Das and S.Bandyopadhyay. 2009. Word to Sentence Level Emotion Tagging for Bengali Blogs. ACL-IJCNLP-2009, pp.149-152. Suntec, Singapore. pdf
  • B. G. Patra, H. Takamura, D. Das , M. Okumura and S. Bandyopadhyay. 2013. Construction of Emotional Lexicon Using Potts Model. In the Proceedings of the International Joint Conference on Natural Language Processing (IJCNLP 2013) , Japan. pdf
  • D. Das and S. Bandyopadhyay. 2010. Labeling Emotion in Bengali Blog Corpus – A Fine Grained Tagging at Sentence Level. In the 8th Workshop on Asian Language Resources (ALR8), 23rd International Conference on Computational Linguistics (COLING 2010), pp. 47-55, August 21-22, Beijing, China. pdf
  • Reyes A., Rosso P. (2014) On the Difficulty of Automatically Detecting Irony: Beyond a Simple Case of Negation. In: Knowledge and Information Systems, 40 (3): 595-614. pdf
  • Ghosh A., Li G., Veale T., Rosso P., Shutova E., Barnden J., Reyes A. (2015). Semeval-2015 task 11: Sentiment Analysis of Figurative Language in Twitter. In: Proc. 9th Int. Workshop on Semantic Evaluation (SemEval 2015), Co-located with NAACL, Denver, Colorado, 4-5 June. Association for Computational Linguistics, pp. 470-478. pdf


Locations of visitors to this page