Enhanced Model for Automatic Tamil Text Summarization

Automatic Text Summarization (ATS) is a process of extracting few text portions from the given document. Such Text can also contain sentence that express the overall meaning of the document. Most of the research work in this field is carried out for Languages like English and Chinese with high accuracy. In this proposed work, hybrid model is used that combines Keyword-based score, sentiment score and Text Ranking-based score to perform Automatic text summarization on Tamil Language. To evaluate the performance of the proposed model, dataset that has been formulated from the scratch by using two reputed Tamil newspapers is considered. The Dataset have been categorized into four classes as Sports, Cinema, Astrology and Politics. The hybrid model increases the accuracy of Tamil text summarization when compared with previous research work. By using the proposed model average accuracy of around 0.81 as Recall score, 0.61 as Precision score and 0.67 as F score is achieved.