Multimodal Subjectivity Analysis of Multiparty Conversation

We investigate the combination of several sources of information for the purpose of subjectivity recognition and polarity classification in meetings. We focus on features from two modalities, transcribed words and acoustics, and we compare the performance of three different textual representations: words, characters, and phonemes. Our experiments show that character-level features outperform wordlevel features for these tasks, and that a careful fusion of all features yields the best performance.1

[1]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[2]  Frederick Jelinek,et al.  Interpolated estimation of Markov source parameters from sparse data , 1980 .

[3]  Jan Svartvik,et al.  A __ comprehensive grammar of the English language , 1988 .

[4]  K. Scherer,et al.  Acoustic profiles in vocal emotion expression. , 1996, Journal of personality and social psychology.

[5]  Jason Eisner,et al.  An Empirical Comparison of Probability Models for Dependency Grammar , 1997, ArXiv.

[6]  Mari Ostendorf,et al.  Detection Of Agreement vs. Disagreement In Meetings: Training With Unlabeled Data , 2003, NAACL.

[7]  Hong Yu,et al.  Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences , 2003, EMNLP.

[8]  Elizabeth Shriberg,et al.  Spotting "hot spots" in meetings: human judgments and prosodic cues , 2003, INTERSPEECH.

[9]  Dan Klein,et al.  Named Entity Recognition with Character-Level Models , 2003, CoNLL.

[10]  Ellen Riloff,et al.  Learning Extraction Patterns for Subjective Expressions , 2003, EMNLP.

[11]  Fuchun Peng,et al.  N-GRAM-BASED AUTHOR PROFILES FOR AUTHORSHIP ATTRIBUTION , 2003 .

[12]  Zoran Obradovic,et al.  Exploiting unlabeled data for improving accuracy of predictive data mining , 2003, Third IEEE International Conference on Data Mining.

[13]  Julia Hirschberg,et al.  Identifying Agreement and Disagreement in Conversational Speech: Use of Bayesian Networks to Model Pragmatic Dependencies , 2004, ACL.

[14]  Soo-Min Kim,et al.  Determining the Sentiment of Opinions , 2004, COLING.

[15]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[16]  Yoram Singer,et al.  BoosTexter: A Boosting-based System for Text Categorization , 2000, Machine Learning.

[17]  Jean Carletta,et al.  The AMI meeting corpus , 2005 .

[18]  Dirk Heylen,et al.  Annotating and measuring meeting behavior , 2005 .

[19]  Oren Etzioni,et al.  Extracting Product Features and Opinions from Reviews , 2005, HLT.

[20]  Johanna D. Moore,et al.  AUTOMATIC TOPIC SEGMENTATION AND LABELING IN MULTIPARTY DIALOGUE , 2006, 2006 IEEE Spoken Language Technology Workshop.

[21]  E. Stamatatos.  Ensemble-based Author Identification Using Character N-grams , 2006 .

[22]  Matthew Purver,et al.  Detecting Action Items in Multi-party Meetings: Annotation and Initial Experiments , 2006, MLMI.

[23]  Dell Zhang,et al.  Extracting key-substring-group features for text classification , 2006, KDD '06.

[24]  Kornel Laskowski,et al.  Emotion recognition in spontaneous speech using GMMs , 2006, INTERSPEECH.

[25]  Richard E. Ladner,et al.  Agreement/Disagreement Classification: Exploiting Unlabeled Data using Contrast Classifiers , 2006, HLT-NAACL.

[26]  Kornel Laskowski,et al.  Annotation and Analysis of Emotionally Relevant Behavior in the ISL Meeting Corpus , 2006, LREC.

[27]  Efstathios Stamatatos,et al.  Webpage Genre Identification Using Variable-Length Character n-Grams , 2007, 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007).

[28]  Swapna Somasundaran,et al.  Detecting Arguing and Sentiment in Meetings , 2007, SIGdial.

[29]  S. Raaijmakers.  Sentiment classification with interpolated information diffusion kernels , 2007, ADKDD '07.

[30]  Wessel Kraaij,et al.  A Shallow Approach to Subjectivity Classification , 2008, ICWSM.

[31]  Theresa Wilson,et al.  Annotating Subjective Content in Meetings , 2008, LREC.