Beyond Sentiment: The Manifold of Human Emotions

Seungyeon Kim, Fuxin Li, Guy Lebanon, Irfan Essa
Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, PMLR 31:360-369, 2013.

Abstract

Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining significant improvements over a baseline without manifold, we are also able to visualize different notions of positive sentiment in different domains.

Cite this Paper

BibTeX
@InProceedings{pmlr-v31-kim13a, title = {Beyond Sentiment: The Manifold of Human Emotions}, author = {Kim, Seungyeon and Li, Fuxin and Lebanon, Guy and Essa, Irfan}, booktitle = {Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics}, pages = {360--369}, year = {2013}, editor = {Carvalho, Carlos M. and Ravikumar, Pradeep}, volume = {31}, series = {Proceedings of Machine Learning Research}, address = {Scottsdale, Arizona, USA}, month = {29 Apr--01 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v31/kim13a.pdf}, url = {https://proceedings.mlr.press/v31/kim13a.html}, abstract = {Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining significant improvements over a baseline without manifold, we are also able to visualize different notions of positive sentiment in different domains.} }
Endnote
%0 Conference Paper %T Beyond Sentiment: The Manifold of Human Emotions %A Seungyeon Kim %A Fuxin Li %A Guy Lebanon %A Irfan Essa %B Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2013 %E Carlos M. Carvalho %E Pradeep Ravikumar %F pmlr-v31-kim13a %I PMLR %P 360--369 %U https://proceedings.mlr.press/v31/kim13a.html %V 31 %X Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining significant improvements over a baseline without manifold, we are also able to visualize different notions of positive sentiment in different domains.
RIS
TY - CPAPER TI - Beyond Sentiment: The Manifold of Human Emotions AU - Seungyeon Kim AU - Fuxin Li AU - Guy Lebanon AU - Irfan Essa BT - Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics DA - 2013/04/29 ED - Carlos M. Carvalho ED - Pradeep Ravikumar ID - pmlr-v31-kim13a PB - PMLR DP - Proceedings of Machine Learning Research VL - 31 SP - 360 EP - 369 L1 - http://proceedings.mlr.press/v31/kim13a.pdf UR - https://proceedings.mlr.press/v31/kim13a.html AB - Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining significant improvements over a baseline without manifold, we are also able to visualize different notions of positive sentiment in different domains. ER -
APA
Kim, S., Li, F., Lebanon, G. & Essa, I.. (2013). Beyond Sentiment: The Manifold of Human Emotions. Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 31:360-369 Available from https://proceedings.mlr.press/v31/kim13a.html.

Related Material