Abstract
This paper describes the iLab-Edinburgh Sentiment Analysis system, winner of the Arabic Twitter Task 7 in SemEval-2016. The system employs a hybrid approach of supervised learning and rule-based methods to predict a sentiment intensity (SI) score for a given Arabic Twitter phrase. First, the supervised method uses an ensemble of trained linear regression models to produce an initial SI score for each given text instance. Second, the resulting SI score is adjusted using a set of rules that exploit a number of publicly available sentiment lexica. The system demonstrates strong results of 0.536 Kendall score, ranking top in this task.
Original language | English |
---|---|
Title of host publication | Proceedings of SemEval 2016 |
Publisher | Association for Computational Linguistics |
Pages | 474-480 |
Number of pages | 7 |
ISBN (Electronic) | 9781941643952 |
Publication status | Published - 2016 |
Event | 10th International Workshop on Semantic Evaluation 2016 - San Diego, California, United States Duration: 16 Jun 2016 → 17 Jun 2016 |
Conference
Conference | 10th International Workshop on Semantic Evaluation 2016 |
---|---|
Abbreviated title | SemEval 2016 |
Country/Territory | United States |
City | San Diego, California |
Period | 16/06/16 → 17/06/16 |
ASJC Scopus subject areas
- Theoretical Computer Science
- Computational Theory and Mathematics
- Computer Science Applications