Evidential Fusion for Sentiment Polarity Classification

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


This paper presents an evidential fusion approach for senti- ment classification tasks and a comparative study with linear sum com- bination. It involves the formulation of sentiment classifier output in the triplet evidence structure and adaptation of combination formulas for combining simple support functions derived from triplet functions by using Smets’s rule, the cautious conjunctive rules and linear sum rule. Empirical comparisons on the performance have been made in individ- uals and in combinations by using these rules, the results demonstrate that the best ensemble classifiers constructed by the four combination rules outperform the best individual classifiers over two public datasets of MP3 and Movie-Review.
Original languageEnglish
Title of host publicationUnknown Host Publication
EditorsFabio Cuzzolin
Number of pages9
Publication statusPublished - 1 Aug 2014
Event3rd International Conference on Belief Functions 2014 - Oxford
Duration: 1 Aug 2014 → …


Conference3rd International Conference on Belief Functions 2014
Period1/08/14 → …

Bibliographical note

Reference text: 1. Feldnan, R.: Techniques and Applications for Sentiment Analysis. Communications of the ACM 56(4), 82–89 (2013)
2. Bi, Y., Guan, J.W., Bell, D.: The combination of multiple classifiers using an evidential approach. Artificial Intelligence 17, 1731–1751 (2008)
3. Denoeux, T.: Conjunctive and disjunctive combination of belief functions induced by nondistinct bodies of evidence. Artificial Intelligence 172(2-3), 234–264 (2008)
4. Smets, P., Kennes, R.: The transferable belief model. Artificial Intelligence 66, 191–243 (1994)
5. Shafer, G.: A Mathematical Theory of Evidence, 1st edn. Princeton University Press, Princeton (1976)
6. Bi, Y.: An Efficient Triplet-based Algorithm for Evidential Reasoning. International Journal of Intelligent Systems 23(4), 1–34 (2008)
7. Srivastava, R.: Alternative form of Dempster’s rule for binary variables. International Journal of Intelligent Systems 20(8), 789–797 (2005)
8. Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools and techniques, 3rd edn. Morgan Kaufmann, San Francisco (2011)
9. Kim, S., Pantel, P., Chklovski, T., Pennacchiotti, M.: Automatically assessing re- view helpfulness. In: Proceedings of the Conference on Empirical Methods in Nat- ural Language Processing (EMNLP), Sydney, Australia, pp. 423–430 (July 2006)
10. Internet Movie Database (IMDb) archive, http://reviews.imdb.com/Reviews/


  • Belief functions
  • combination rules
  • linear sum and senti- ment polarity classification.


Dive into the research topics of 'Evidential Fusion for Sentiment Polarity Classification'. Together they form a unique fingerprint.

Cite this