@inproceedings{4bd582d45b014df1b43affdc477c226a,
title = "Semantic text classification with tensor space model-based na{\"i}ve Bayes",
abstract = "This paper presents a semantic na{\"i}ve Bayes classification technique that is based upon our tensor space model for text representation. In our work, each of Wikipedia articles is defined as a single concept, and a document is represented as a 2nd-order tensor. Our method expands the conventional na{\"i}ve Bayes by incorporating the semantic concept features into term feature statistics under the tensor-space model. Through extensive experiments using three popular document collections, we prove that the proposed method significantly outperforms the conventional na{\"i}ve Bayes. Surprisingly, the classification performance amounts to almost 100% in terms of F1-measures when using Reuters-21578 and 20Newsgroups document collections.",
keywords = "Concepts, Na{\"i}ve Bayes, Semantics, Tensor space, Text classification, Vector space, Wikipedia",
author = "Kim, {Han Joon} and Jiyun Kim and Jinseog Kim",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 ; Conference date: 09-10-2016 Through 12-10-2016",
year = "2017",
month = feb,
day = "6",
doi = "10.1109/SMC.2016.7844892",
language = "English",
series = "2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4206--4210",
booktitle = "2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings",
address = "United States",
}