Hierarchical neural networks for text categorization (poster abstract)
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
The Structure of a Semantic Neural Network Extracting the Meaning from a Text
Cybernetics and Systems Analysis
Hierarchical Text Categorization Using Neural Networks
Information Retrieval
Data Mining: Concepts and Techniques
Data Mining: Concepts and Techniques
Using appraisal groups for sentiment analysis
Proceedings of the 14th ACM international conference on Information and knowledge management
Thumbs up?: sentiment classification using machine learning techniques
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Sentiment analysis in multiple languages: Feature selection for opinion classification in Web forums
ACM Transactions on Information Systems (TOIS)
Exploring the characteristics of opinion expressions for political opinion classification
dg.o '08 Proceedings of the 2008 international conference on Digital government research
Automatic document prior feature selection for web retrieval
Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
Opinion Mining and Sentiment Analysis
Foundations and Trends in Information Retrieval
Hi-index | 0.00 |
Sentiment analysis has attracted more and more attention in recent years. Neural network can be trained to calculate the sentiment orientation value of the text. After getting the value, a turning point is used to identify the text polarity. The midpoint 0.5 is often used as the turning point, however, we show in this paper that the midpoint is not always good for getting the highest classification precision. In the paper, three methods are proposed to find the appropriate turning point. We prepare the book review from Amazon.com and experiment our three methods. Neural Network classifier is employed in experiments and the results show the better precision compared with midpoint method.