@inproceedings{216a4ca18e344f63bb6fc0439aa78602,
title = "Improving classification performance by extending documents terms",
abstract = "Classification is a technique in data mining for categorizing objects. Text Classification is re-challenged for classifying very short documents or text as shown in social media collection. This paper proposes a method to improve the performance of classification on short documents. In this work, we expand words in every document before the documents are classified We use TFIDF model, Hidden Markov Model k-means clustering, and Latent Semantic Indexing (LSI) for expanding documents. The results show that extending document term by just 1 word will increase its accuracy, while extending by 2,4, and 8 words tend to give stable results.",
keywords = "Hidden Markov Model k-means, Latent Semantic Indexing, TFIDF model, extend words, text classification",
author = "Widodo and Wibowo, \{Wahyu Catur\}",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 International Conference on Data and Software Engineering, ICODSE 2014 ; Conference date: 26-11-2014 Through 27-11-2014",
year = "2014",
month = mar,
day = "17",
doi = "10.1109/ICODSE.2014.7062657",
language = "English",
series = "Proceedings of 2014 International Conference on Data and Software Engineering, ICODSE 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of 2014 International Conference on Data and Software Engineering, ICODSE 2014",
address = "United States",
}