Output details
11 - Computer Science and Informatics
University of Birmingham
Output title
A CCG-Based Approach to Fine-Grained Sentiment Analysis
Type
E - Conference contribution
DOI
-
Name of conference/published proceedings
Proceedings of the 2nd Workshop on Sentiment Analysis where AI meets Psychology , SAAIP 2012. : COLING 2012 Workshop
Volume number
-
Issue number
-
First page of article
3
ISSN of proceedings
-
Year of publication
2012
Number of additional authors
1
Additional information
<22>Describes a system which uses CCG parsing to do sentiment analysis on text. The system is tested on data developed for the SemEval 2007 sentiment analysis research competition and is shown to perform better than the leading competition systems. We also reannotated the data with a more sophisticated model of emotion and demonstrate that the system is capable of fine-grained analysis. The underlying algorithm has been adopted by an ongoing Dstl research project on automated analysis of twitter feeds. The paper was published in a specialised workshop affiliated with COLING2012, one of the two top NLP conferences internationally.
Interdisciplinary
-
Cross-referral requested
-
Research group
A - Artificial Intelligence and Intelligent Robotics
Citation count
-
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
