Abstract | ||
---|---|---|
Sentiment classification is a useful approach to analyse the emotional polarity of user reviews, and method based on machine learning has achieved a great success. In the era of Web2.0, the emotional intensity of terms will change with time and events, while a large number of Out-Of-Vocabulary (OOV) terms are appearing. But the method of machine learning pays little attention to them because they focus to reduce the computational complexity. To address the problem, we proposed a dynamic forest model, which can describe the emotional intensity of the term in character granularity, and can append OOV dynamically and adjust their emotional intensity value. Experiments show that in the Chinese environment, our model greatly boosts the performance compared with the method based machine learning, while the time is saved by halves. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-70139-4_21 | NEURAL INFORMATION PROCESSING, ICONIP 2017, PT V |
Keywords | Field | DocType |
Sentiment classification, Machine learning, Out-Of-Vocabulary, Sentiment lexicon, Dynamic forest | Computer science,Append,Artificial intelligence,Out of vocabulary,Granularity,Machine learning,Computational complexity theory | Conference |
Volume | ISSN | Citations |
10638 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingming Li | 1 | 34 | 9.46 |
Jiao Dai | 2 | 0 | 1.01 |
Wei Liu | 3 | 4041 | 204.19 |
Jizhong Han | 4 | 355 | 54.72 |