Summary of the paper
| Title | Automatic Annotation of Word Emotion in Sentences Based on Ren-CECps |
|---|---|
| Authors | Changqin Quan and Fuji Ren |
| Abstract | Textual information is an important communication medium containedrich expression of emotion, and emotion recognition on text has wideapplications.Word emotion analysis is fundamental in the problem oftextual emotion recognition. Through an analysis of the characteristicsof word emotion expression, we use word emotion vector to describe thecombined basic emotions in a word, which can be used to distinguishdirect and indirect emotion words, express emotion ambiguity in words,and express multiple emotions in words. Based onRen-CECps (a Chinese emotion corpus), we do anexperiment to explore the role of emotion word for sentence emotionrecognition and we find that the emotions of asimple sentence (sentence without negative words, conjunctions,or question mark) can be approximated by an addition of theword emotions. Then MaxEnt modeling is used to find which contextfeatures are effective for recognizing word emotion in sentences. Thefeatures of word, N-words, POS, Pre-N-words emotion,Pre-is-degree-word, Pre-is-negativeword, Pre-is-conjunction and theircombination have been experimented. After that, we use the two metrics:Kappa coefficient of agreement and Voting agreement to measurethe word annotation agreement of Ren-CECps. The experiments on above contextfeatures showed promising results compared with word emotion agreement onpeople's judgments. |
| Language | |
| Topics | Emotion Recognition/Generation |
Full paper  |
Automatic Annotation of Word Emotion in Sentences Based on Ren-CECps |
| Bibtex | @InProceedings{QUAN10.662, author = {Changqin Quan and Fuji Ren}, title = {Automatic Annotation of Word Emotion in Sentences Based on Ren-CECps}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |