A Topic Partition Algorithm Based on Average Sentence Similarity for Interactive Text

Download PDF
Open Webpage

Haiping Zhu, Yan Chen, Yang Yang, Chao Gao

Published: 2011, Last Modified: 21 Jan 2026CIS 2011EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Based on the research and analysis of interactive text properties, the word frequency statistics and synonyms merger are imported to obtain the keywords of interactive text. The Sentence similarity is used to describe the degree of coupling between sentences. Then a novel topic partition algorithm based on average sentence similarity is proposed. The experimental results show the effectiveness of the algorithm. Along with the mining of the deep correlations among texts, the algorithm precision and accuracy will be improved.