Recent Papers

We propose a collaborative multi-Trends sentiment classification approach to train sentiment tweets simultaneously. Specifically, we decompose the sentiment classifier of each trend into two components, a global one and a Trends-specific one. Automatically identifies the important aspects of topics from online consumer reviews. We analyse and experiment with a set of straight forward language-independent features based on the social spread of trends to categorize them into the introduced typology as news, ongoing events, memes and commemoratives. The global model can capture the general sentiment knowledge and is shared by various tweets. The Trends-specific Greedy & Dynamic Blocking Algorithms like model can capture the specific sentiment expressions in each Trend. In addition, we extract Trends-specific sentiment knowledge from both labeled and unlabeled samples in each Trend and use it to enhance the learning of Trends-specific sentiment classifiers. Two kinds of Trends similarity measures are explored, one based on textual content and the other one based on sentiment expressions. Moreover, we introduce two efficient algorithms to solve the model of our approach. Experimental results on benchmark datasets show that our approach can effectively improve the performance of multi-Trends sentiment classification and significantly outperform baseline methods.

Copyright © 2023 Rajavenkatesswaran K C, Nareshkumar V, Nithesh Kumar M, Praveen Kumar, Vairaprakash M. This is an open access article distributed under the Creative Commons Attribution License.