Aspect-Based Sentiment Analysis for people reviews for aspect analysis
- Author Rajveer kaur,
- Co-Author Sandeep Kautish
- DOI
- Country : India
- Subject : Computer Engineering
Keywords : Lexical, Text Mining, statistical
Abstract
Text mining could be a technique to search out significant patterns from the on the market text documents. A number of experiments have been conducted over the proposed model by using the various forms of the input data generated after various levels of pre-processing. The proposed model has been tested for the various performance measures which includes the precision, recall, average prediction accuracy and F1-measures. All of the above performance measures has been obtained after the estimation of the statistical type 1 and type 2 errors over the input data. The proposed model has been found accurate higher than 60-85% in all of the rounds if the true negative cases are also being analyzed. The proposed model has been recorded with the average accuracy over all of the test cases nearly at 83% which is better all of the other models used under the existing model. The proposed model has outperformed all of the existing models designed with the different filters over the differently processed datasets.
Comments
No have any comment !