W
Wang Kaige
Researcher at Chongqing University
Publications - 5
Citations - 52
Wang Kaige is an academic researcher from Chongqing University. The author has contributed to research in topics: Sentiment analysis & Word embedding. The author has an hindex of 2, co-authored 5 publications receiving 12 citations.
Papers
More filters
Proceedings ArticleDOI
Multi-modal cyberbullying detection on social networks
TL;DR: This work proposes a multi-modal cyberbullying detection framework that takes into multi- modal information on social networks, and uses the hierarchical attention networks to capture the session feature in social networks and encode several media information.
Journal ArticleDOI
Residual attention and other aspects module for aspect-based sentiment analysis
TL;DR: Zhang et al. as mentioned in this paper proposed two models named RA-CNN and RAO-CNN for aspect-based sentiment analysis (ABSA) task, which can reduce interference of sentiment information related to other aspect terms in multi-aspect text.
Journal ArticleDOI
A relative position attention network for aspect-based sentiment analysis
TL;DR: This work proposes an improved model based on convolutional neural networks that extracts more useful information and analyzes the sentiment more accurately in the comment text and outperforms to other state-of-the-art methods.
Patent
Aspect-level sentiment analysis method based on convolutional neural network
TL;DR: In this article, an aspect-level sentiment analysis method based on a convolutional neural network (CNN) was proposed, which comprises the steps of establishing an aspect level sentiment analysis model, constructing a relative position matrix of aspect-Level information in the text through the model, fusing the text codes with the text code, extracting a part of incidence matrixes corresponding to aspect-LSTM, and extracting the aspect-lSTM associated with the aspect level information in these matrixes.
Patent
High-power microwave heating early warning system and method based on infrared thermal imaging
TL;DR: In this paper, a high-power microwave heating early warning system and method based on infrared thermal imaging is presented, where the temperature distribution and the highest temperature value of an industrial material in a high powermicrowave heating environment can be acquired in real time, the temperature change of the heated material is intelligently adjusted according to the highest value of the area, and safety accidents caused by overhigh temperature of a local area are effectively avoided.