%0 Report %1 holzman03classification %A Holzman, L. E. %A Pottenger, W. M. %D 2003 %K chat, emotion, extraction, nlp, speech %T Classification Of Emotions in Internet Chat: An Application of Machine Learning Using Speech Phonemes %U http://www.cs.umass.edu/\~lholzman/papers/EmotionClassification.pdf %X This article reports our progress in the classification of expressions of emotion in network-based chat conversations. Emotion detection of this nature is currently an active area of research 8 9. We detail a linguistic approach to the tagging of chat conversation with appropriate emotion tags. In our approach, textual chat messages are automatically converted into speech and then instance vectors are generated from frequency counts of speech phonemes present in each message. In combination with other statistically derived attributes, the instance vectors are used in various machine-learning frameworks to build classifiers for emotional content. Based on the standard metrics of precision and recall, we report results exceeding 90\% accuracy when employing k-nearest-neighbor learning. Our approach has thus shown promise in discriminating emotional from non-emotional content in independent testing.

@techreport{holzman03classification, abstract = {{This article reports our progress in the classification of expressions of emotion in network-based chat conversations. Emotion detection of this nature is currently an active area of research [8] [9]. We detail a linguistic approach to the tagging of chat conversation with appropriate emotion tags. In our approach, textual chat messages are automatically converted into speech and then instance vectors are generated from frequency counts of speech phonemes present in each message. In combination with other statistically derived attributes, the instance vectors are used in various machine-learning frameworks to build classifiers for emotional content. Based on the standard metrics of precision and recall, we report results exceeding 90\% accuracy when employing k-nearest-neighbor learning. Our approach has thus shown promise in discriminating emotional from non-emotional content in independent testing.}}, added-at = {2010-12-17T18:47:41.000+0100}, author = {Holzman, L. E. and Pottenger, W. M.}, biburl = {https://www.bibsonomy.org/bibtex/257762adf8b216dc5bbf9bf8181589670/mortimer_m8}, citeulike-article-id = {336966}, citeulike-linkout-0 = {http://www.cs.umass.edu/\~{}lholzman/papers/EmotionClassification.pdf}, comment = {the author transforms the chat text in speech and uses feature (like phoneme count, etc..) to classify sentences emotions. They use statistical method to train a classifier on a corpus they created.}, institution = {Lehigh University}, interhash = {7ec8e7b38ebe0e1e7485baa4f192f218}, intrahash = {57762adf8b216dc5bbf9bf8181589670}, keywords = {chat, emotion, extraction, nlp, speech}, posted-at = {2005-09-30 15:01:39}, priority = {0}, timestamp = {2010-12-20T11:11:25.000+0100}, title = {{Classification Of Emotions in Internet Chat: An Application of Machine Learning Using Speech Phonemes}}, url = {http://www.cs.umass.edu/\~{}lholzman/papers/EmotionClassification.pdf}, year = 2003 }