Paper: Recognition of Sentiment Sequences in Online Discussions

ACL ID W14-5907
Title Recognition of Sentiment Sequences in Online Discussions
Venue Workshop on Natural Language Processing for Social Media
Session  
Year 2014
Authors

Currently 19%-28% of Internet users participate in online health discussions. In this work, we study sentiments expressed on online medical forums. As well as considering the predominant sentiments expressed in individual posts, we analyze sequences of sentiments in online discus- sions. Individual posts are classified into one of the five categories encouragement, gratitude, confusion, facts, and endorsement. 1438 messages from 130 threads were annotated manually by two annotators with a strong inter-annotator agreement (Fleiss kappa = 0.737 and 0.763 for posts in sequence and separate posts respectively). The annotated posts were used to analyse sentiments in consecutive posts. In automated sentiment classification, we applied HealthAf- fect, a domain-specific lexicon of affective ...

@InProceedings{bobicev-sokolova-oakes:2014:SocialNLP,
  author    = {Bobicev, Victoria  and  Sokolova, Marina  and  Oakes, Michael},
  title     = {Recognition of Sentiment Sequences in Online Discussions},
  booktitle = {Proceedings of the Second Workshop on Natural Language Processing for Social Media (SocialNLP)},
  month     = {August},
  year      = {2014},
  address   = {Dublin, Ireland},
  publisher = {Association for Computational Linguistics and Dublin City University},
  pages     = {44--49},
  url       = {http://www.aclweb.org/anthology/W14-5907}
}