News & Events

Department of Chinese, Translation and Linguistics

Research Degree Forum

Combining A Large Sentiment Lexicon and Machine Learning for Subjectivity Classification

 Presented by

Mr. LU Bin

PhD candidate, Department of Chinese, Translation and Linguistics, City University of Hong Kong

Date: 5 August 2010, Thursday
Time: 3:30 - 4:30 pm
Venue: B7603 (7/F, Blue Zone), Academic Building, CityU

Abstract

In recent years, the analysis of opinions from information sources such as news, blogs and product reviews has drawn much attention in the NLP field. It has many applications such as social media monitoring, market research, and public relations. To analyze opinions in texts, we first need to distinguish opinions from facts, which could be done in the sentence level, i.e. to identify opinionated sentences in texts. This task of identifying opinionated sentences is called subjectivity classification.

Most previous work on subjectivity classification bases on either machine learning techniques (such as SVM, Maximum Entropy, Naive Bayes, etc.) or general sentiment lexicons. This paper presents an empirical study on combining a large sentiment lexicon and machine learning techniques for opinion analysis:
1) a large sentiment lexicon is automatically adjusted according to training data;
2) machine learning techniques are used to learn models on training data;
3) the results given by machine learning classifiers and the supervised lexicon-based classifier are combined to get better results.
The experiments with the NTCIR data show that our approach significantly outperforms the baselines on subjectivity classification, i.e. the adjusted large sentiment lexicon shows good performance and its combination with machine learning techniques shows further improvement.

Speaker