Abstract | ||
---|---|---|
Target-level sentiment analysis (TLSA) is a classification task to extract sentiments from targets in text. In this paper, we propose target-dependent convolutional neural network (TCNN) tailored to the task of TLSA. The TCNN leverages the distance information between the target word and its neighboring words to learn the importance of each word to the target. Experimental results show that the TCNN achieves state-of-the-art performance on both single- and multi-target datasets. Qualitative evaluations were conducted to demonstrate the limitations of previous TLSA methods and also to verify that distance information is crucial for TLSA. Furthermore, by exploiting a convolutional neural network (CNN), the TCNN trains six times faster per epoch than other baselines based on recurrent neural networks. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.ins.2019.03.076 | Information Sciences |
Keywords | Field | DocType |
Sentiment anlaysis,Target-level sentiment analysis (TLSA),Word distance,Deep learning,Convolutional neural network (CNN) | Convolutional neural network,Sentiment analysis,Qualitative Evaluations,Recurrent neural network,Artificial intelligence,Mathematics,Machine learning | Journal |
Volume | ISSN | Citations |
491 | 0020-0255 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dongmin Hyun | 1 | 7 | 2.82 |
Chanyoung Park | 2 | 163 | 12.04 |
Min-Chul Yang | 3 | 98 | 4.72 |
Ilhyeon Song | 4 | 2 | 0.69 |
Jungtae Lee | 5 | 224 | 27.97 |
Hwanjo Yu | 6 | 1715 | 114.02 |