Multilingual Opinion Analysis at NTCIR-7
We developed a supervised approach to the opinionated and the polarity subtasks. We applied a sequential tagging approach at the token level and used the learned token labels in the sentence-level classification tasks. In our formal run submissions, we utilized SVMhmm in both tasks with syntactic and lexicon-based features.
Our system ranked 2nd out of 9 systems in the opinionated sentence classification subtask and 3rd out of 5 systems in the polarity classification subtask.
A full description of the task, including results from all systems, is available in the organizer's report. A detailed description of our system is available in the following paper:
- Lizhen Qu and Cigdem Toprak and Niklas Jakob and Iryna Gurevych. Sentence Level Subjectivity and Sentiment Analysis Experiments in NTCIR-7 MOAT Challenge. In Proceedings of the 7th NTCIR Workshop Meeting on Evaluation of Information Access Technologies: Information Retrieval, Question Answering, and Cross-Lingual Information Access, pages 210–217, December 2008.