论文信息 - Emotion Analysis of Internet Chat

Emotion Analysis of Internet Chat

We present a system for Emotion Analysis of Instant Messages (IM). Using Instance Based classifier we have shown that our system can outperform similar systems in the IM domain. Tagged instant messages and elaborate feature engineering can help a lot in increasing the performance of text classification of unstructured, ungrammatical text. The impact of class imbalance on classification has been studied and demonstration has been made of how undersampling can help mitigate this problem.

Pushpak Bhattacharyya

[1] P. Ekman,et al. The Repertoire of Nonverbal Behavior: Categories, Origins, Usage, and Coding , 1969 .

[2] Henry Lieberman,et al. A model of textual affect sensing using real-world knowledge , 2003, IUI '03.

[3] Nathalie Japkowicz,et al. The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[4] Stan Szpakowicz,et al. Identifying Expressions of Emotion in Text , 2007, TSD.

[5] Craig H. Martell,et al. Lexical and Discourse Analysis of Online Chat Dialog , 2007, International Conference on Semantic Computing (ICSC 2007).

[6] William M. Pottenger,et al. Classification of Emotions in Internet Chat: An Application of Machine Learning Using Speech Phonemes , 2003 .

[7] T. Danisman,et al. Feeler: Emotion Classification of Text Using Vector Space Model , 2008 .

[8] Claire Cardie,et al. Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[9] Alan P. Schmidt. Detection of Topic Change in IRC Chat Logs , 2003 .

[10] Anthony C. Boucouvalas,et al. Real Time Text-to-Emotion Engine for Expressive Internet Communications , 2003 .

[11] Carlo Strapparava,et al. Learning to identify emotions in text , 2008, SAC '08.

[12] Gongping Yang,et al. On the Class Imbalance Problem , 2008, 2008 Fourth International Conference on Natural Computation.

[13] S. Tagliamonte,et al. LINGUISTIC RUIN? LOL! INSTANT MESSAGING AND TEEN LANGUAGE , 2008 .