My research is centered around textual sentiment analysis.
In a computational context, sentiment (cf. emotion, affect, tone, opinion, private state, speculation, evaluation, appraisal, attitude, attitudinal meaning, bias, colouring, connotation, slanting, stance, amongst others) refers to the enormously rich subjective metacontent that lies beyond the purely objective (or factual, logical, neutral) dimensions of language.
Linguistics. The primary linguistic focus of my research is on
* fine-grained sentiment expressions at the word, entity, phrase, and sentence levels
* sentiment with respect to lexical semantics, morphology, grammar, and compositional semantics
* affective commonsense
Computational Linguistics / Natural Language Processing. Computationally, I aim at combining the above with
* deep parsing
* phrase chunking
* Named Entity Recognition
* Word Sense Disambiguation
Packed Feelings and Ordered Sentiments: Sentiment Parsing with Quasi−compositional Polarity Sequencing and Compression
Karo Moilanen‚ Stephen Pulman and Yue Zhang
In Proceedings of the 1st Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA 2010) at the 19th European Conference on Artificial Intelligence (ECAI 2010). Pages 36–43. August, 2010.
Leveraging Textual Sentiment Analysis with Social Network Modelling: Sentiment Analysis of Political Blogs in the 2008 U.S. Presidential Election
Multi−entity Sentiment Scoring
Karo Moilanen and Stephen Pulman
In Proceedings of Recent Advances in Natural Language Processing (RANLP 2009). Pages 258–263. September, 2009.