Sentence-Level Emotion and Valence Tagging


The paper proposes the tagging of sentence-level emotion and valence based on the word-level constituents on the SemEval 2007 affect sensing news corpus. The baseline system for each emotion class assigns the class label to each word, while the WordNet Affect lists updated using the SentiWordNet were also used as the lexicon-based system. Though the inclusion of morphology into the lexicon-based system improves the performance of the word-level emotion tagging, the Conditional Random Field-based machine-learning framework was employed for the word-level emotion-tagging system, and it outperforms both the baseline- and lexicon-based systems. Six separate sense scores for six emotion types are calculated from the SentiWordNet and applied to word-level emotion tagged constituents for identifying sentential emotion scores. Three emotion scoring methods followed by a post-processing technique were employed for identifying the sentence-level emotion tags. In addition to that, the best two emotion tags corresponding to the maximum obtained sense scores are assigned to the sentences, whereas the sentence-level valence is identified based on the total sense scores of the word-level emotion tags along with their polarity. Evaluation was carried out with respect to the best two emotion tags on 250 gold standard test sentences and achieved satisfactory results for sentence-level emotion and valence tagging.

This is a preview of subscription content, access via your institution.

Fig. 1


  1. 1.


  1. 1.

    Zhang Y, Li Z, Ren F, Kuroiwa S. A preliminary research of Chinese emotion classification model. IJCSNS. 2008;8(11):127–32.

    Google Scholar 

  2. 2.

    Salovey P, Mayer J. Emotional intelligence. Imagin Cogn Pers. 1990;9(3):185–211.

    Article  Google Scholar 

  3. 3.

    Strapparava C, Valitutti A. Wordnet-affect: an affective extension of wordnet. 4th LREC; 2004. p. 1083–86.

  4. 4.

    Quirk R, Greenbaum S, Leech G, Svartvik J. A comprehensive grammar of the English language. New York: Longman; 1985.

    Google Scholar 

  5. 5.

    Grefenstette G, Qu Y, Shanahan JG, Evans DA. Coupling niche browsers and affect analysis for an opinion mining application. 2004.

  6. 6.

    Sood S, Vasserman L. ESSE: exploring mood on the web. In: Proceedings of the 3rd international AAAI conference on weblogs and social media (ICWSM) data challenge workshop; 2009.

  7. 7.

    Wiebe J, Wilson T, Rebecca F, Bell M, Martin M. Learning subjective language. Comput Linguist. 2004;30:277–308.

    Article  Google Scholar 

  8. 8.

    Turney PD. 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; 2002. p. 417–24.

  9. 9.

    Lin KH-Y, Yang C, Chen H–H. What emotions news articles trigger in their readers? In: Proceedings of SIGIR; 2007. p. 733–34.

  10. 10.

    Yang C, Lin KHY, Chen HH. Emotion classification using web blog corpora. In: IEEE, WIC, ACM international conference on web intelligence; 2007. p. 275–78.

  11. 11.

    Cardie C, Wiebe J, Wilson T, Litman JD. Combining low-level and summary representations of opinions for multi-perspective question answering. N Direct Quest Answ 2003; 20–7.

  12. 12.

    Pang B, Lee L. Opinion mining and sentiment analysis. Found Trends Inf Retr 2 2008;1–2:1–135.

    Google Scholar 

  13. 13.

    Ekman P. Facial expression and emotion. Am Psychol. 1993;48(4):384–92.

    PubMed  Article  CAS  Google Scholar 

  14. 14.

    Strapparava C, Mihalcea R. SemEval-2007 task 14: affective text. In: Proceedings of the 45th annual meeting of association for computational linguistics; 2007.

  15. 15.

    Cohen J. A coefficient of agreement for nominal scales. Educ Psychol Meas. 1960;20:37–46.

    Article  Google Scholar 

  16. 16.

    Strapparava C, Valitutti A. WordNet-Affect: an affective extension of WordNet. In: Proceedings of the 4th international conference on language resources and evaluation; 2004. p. 1083–86.

  17. 17.

    Baccianella S, Esuli A, Sebastiani F. SentiWordNet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. In Proceedings of LREC-10, 7th conference on language resources and evaluation; 2010. p. 2200–04.

  18. 18.

    Miller GA. WordNet: an on-line lexical database. Int J Lexicography. 1990;3(4):235–312.

    Article  Google Scholar 

  19. 19.

    Lafferty J, McCallum A, Pereira F. Conditional random fields: probabilistic models for segmenting and labelling sequence data. iN: Proceeding ICML ‘01 of the eighteenth international conference on machine learning; 2001.

  20. 20.

    Torii Y, Das D, Bandyopadhyay S, Okumura M. Developing Japanese WordNet affect for analyzing emotions. In: proceedings of the 2nd workshop on computational approaches to subjectivity and sentiment analysis (WASSA 2.011), 49th annual meeting of the association for computational linguistics: human language technologies (ACL-HLT 2011), Portland; 2011. p. 80–6.

  21. 21.

    Cardie C, Wiebe J, Wilson T. Annotating expressions of opinions and emotions in language. Lang Resour Eval. 2005;39(2):65–210.

    Google Scholar 

  22. 22.,en/.

  23. 23.

  24. 24.

    Alm CO, Roth D, Sproat R. Emotions from text: machine learning for text-based emotion prediction. In: Proceedings of the conference on human language technology and empirical methods in natural language processing. Vancouver; 2005. p. 579–86.

  25. 25.

    Manning CD, Toutanova K. Enriching the knowledge sources used in a maximum entropy part-of-speech tagger. In: Proceedings of the joint SIGDAT conference on empirical methods in natural language processing and very large corpora (EMNLP/VLC); 2000.

  26. 26.

    Das D, Bandyopadhyay S. Word to sentence level emotion tagging for Bengali blogs. ACL-IJCNLP 2009; 2009, p. 149–52.

  27. 27.

    Liu H, Lieberman H, Selker T. A model of textual affect sensing using real-world knowledge. In: IUI ‘03: proceedings of the 8th international conference on intelligent user interfaces, ACM; 2003.

  28. 28.

    Wilson T, Wiebe J, Hwa R. Just how mad are you? Finding strong and weak opinion clauses. In: Proceedings of the nineteenth national conference on artificial intelligence (AAAI); 2004. p. 761–69.

  29. 29.

    Sebastiani F. Machine learning in automated text categorization. ACM Comput Surv 2002;34(1).

  30. 30.

    Mishne G, de Rijke M. Capturing global mood levels using blog posts. In: Proceedings of AAAI, spring symposium on computational approaches to analysing weblogs; 2006. p. 145–52.

  31. 31.

    Ku L-W, Liang Y-T, Chen HH. Opinion extraction, summarization and tracking in news and blog corpora. In: AAAI-2006 spring symposium on computational approaches to analyzing weblogs, AAAI technical report; 2006. p. 100–07.

  32. 32.

    Das D, Bandyopadhyay S. Sentence level emotion tagging. In: The proceedings of the 2009 international conference on affective computing & intelligent interaction (ACII-2009). Amsterdam; 2009. p. 375–80. doi:10.1109/ACII.2009.5349598.

  33. 33.

    de Albornoz JC, Plaza L, Gervás P. A hybrid approach to emotional sentence polarity and intensity classification. In: Proceedings of the fourteenth conference on computational natural language learning, ACL, Uppsala; 2010. p. 153–61.

  34. 34.

    Liu B. The challenge is still the accuracy of sentiment prediction and solving the associated problems. In: 5th annual text analytics summit; 2009.

  35. 35.

    Das D, Bandyopadhyay S. Identifying emotional expressions, intensities and sentential emotion tags using a supervised framework. In: proceedings of the 24th Pacific Asia conference on language, information and computation (PACLIC), Sendai; 2010. p. 95–4, Nov 4–7.

  36. 36.

    Hatzivassiloglou V, McKeown K. Predicting the semantic orientation of adjectives. In: Proceedings of ACL; 1997. p. 174–81.

  37. 37.

    Pang B, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP); 2002. p. 79–6.

  38. 38.

    Iadh O, Craig M, Ian S. Overview of the TREC2008 blog track. TREC-2008; 2008.

  39. 39.

    Seki Y, Evans DK, Ku LW, Chen HH, Kando N, Lin CY. Overview of opinion analysis pilot task at NTCIR-6. NTCIR-6; 2006.

  40. 40.

    Chaumartin FR. UPAR7: a knowledge-based system for headline sentiment tagging. In: Proceedings of the 4th international workshop on semantic evaluations (SemEval-2007), Association for Computational Linguistics; 2007. p. 422–25.

Download references


The work reported in this article was supported by a grant from the India-Japan cooperative programme (DST-JST) 2009 research project entitled “Multidisciplinary Research Field on Sentiment Analysis where AI meets Psychology” funded by the Department of Science and Technology (DST), Government of India.

Author information



Corresponding author

Correspondence to Dipankar Das.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Das, D., Bandyopadhyay, S. Sentence-Level Emotion and Valence Tagging. Cogn Comput 4, 420–435 (2012).

Download citation


  • Emotion
  • Valence
  • WordNet Affect
  • SentiWordNet
  • CRF