A semi-supervised tweet classification method using news articles

Hong, Beomseok; Han, Youngsub; Kim, Yanggon

doi:10.1145/2811411.2811478

Cited by 1 publication

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The threshold for the body feature is already determined at 15% of the total number of the news articles in the previous research [9].…”

Section: B Threshold For Extracting Topic Signaturesmentioning

confidence: 99%

“…In previous research studies, we proposed a system for discriminating company names in Twitter based on knowledge from news content without manual annotations [9]. Despite the fact that the New York Times APIs provide a variety of features such as abstracts, headlines, lead paragraphs, and snippets, the previous system utilized only the main text of the newspaper (i.e., body of each article) for automatic word sense discrimination.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Company Name Discrimination in Tweets using Topic Signatures Extracted from News Corpus

Hong¹,

Kim²,

Lee³

2016

Journal of Computing Science and Engineering

Self Cite

View full text Add to dashboard Cite

It is impossible for any human being to analyze the more than 500 million tweets that are generated per day. Lexical ambiguities on Twitter make it difficult to retrieve the desired data and relevant topics. Most of the solutions for the word sense disambiguation problem rely on knowledge base systems. Unfortunately, it is expensive and time-consuming to manually create a knowledge base system, resulting in a knowledge acquisition bottleneck. To solve the knowledgeacquisition bottleneck, a topic signature is used to disambiguate words. In this paper, we evaluate the effectiveness of various features of newspapers on the topic signature extraction for word sense discrimination in tweets. Based on our results, topic signatures obtained from a snippet feature exhibit higher accuracy in discriminating company names than those from the article body. We conclude that topic signatures extracted from news articles improve the accuracy of word sense discrimination in the automated analysis of tweets.

show abstract

“…The threshold for the body feature is already determined at 15% of the total number of the news articles in the previous research [9].…”

Section: B Threshold For Extracting Topic Signaturesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%