A topic detection method based on Semantic Dependency Distance and PLSA

Author

Chen, Yan ; Yang, Yang ; Zhang, Huisan ; Zhu, Haiping ; Tian, Feng

Author_Institution

Dept. of Comput. Sci. & Technol., Xi´´an Jiaotong Univ., Xi´´an, China

fYear

2012

fDate

23-25 May 2012

Firstpage

703

Lastpage

708

Abstract

Topic detection is a hot topic in the field of text mining. In this paper, focusing on the Chinese interactive text, we explored a novel topic detection method, named SDD-PLSA, which integrates Semantic Dependency Distance (SDD) and PLSA. It not only has the advantages of PLSA, which is an efficient, effective method and is widely used in text mining, but also considers the semantic and syntax information. Thus, the problem of lacking semantic information in PLSA can be avoided. SDD-PLSA has two main steps. The first is using SDD to classify the sentences that have a high similarity in semantics into several groups according to semantic feature extraction of the interactive text. Then, a PLSA classifier is used upon the result of the first step. The experiments show that the accuracy of detection on `love´ topic has been improved to 64.8% when using SDD-PLSA, better than 55.4% when using PLSA.

Keywords

classification; computer aided instruction; data mining; feature extraction; statistical analysis; text analysis; Chinese interactive text; PLSA classifier; SDD-PLSA; e-Iearning systems; probabilistic latent semantic analysis; semantic dependency distance; semantic feature extraction; semantic information; sentence classification; syntax information; text mining; topic detection method; Pragmatics; Semantics; E-learning; Interactive Text; PLSA; Semantic Dependency Distance; Topic Detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Supported Cooperative Work in Design (CSCWD), 2012 IEEE 16th International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4673-1211-0

Type

conf

DOI

10.1109/CSCWD.2012.6221895

Filename

6221895