Combining statistical data analysis techniques to extract topical keyword classes from corpora

Article type: Research Article

Authors: Rossignol, Mathias | Sébillot, Pascale^{; *}

Affiliations: Irisa, Campus de Beaulieu, 35042 Rennes Cedex, France

Correspondence: [*] Corresponding author: Pascale Sébillot. Tel.: +33 2 99 84 73 17; Fax: +33 2 99 84 71 71; E-mail: sebillot@irisa.fr.

Abstract: We present an unsupervised method for the generation from a textual corpus of sets of keywords, that is, words whose occurrences in a text are strongly connected with the presence of a given topic. Each of these classes is associated with one of the main topics of the corpus, and can be used to detect the presence of that topic in any of its paragraphs, by a simple keyword co-occurrence criterion. The classes are extracted from the textual data in a fully automatic way, without requiring any a priori linguistic knowledge or making any assumptions about the topics to search for. The algorithms we have developed allow us to yield satisfactory and directly usable results despite the amount of noise inherent in textual data. That goal is reached thanks to a combination of several data analysis techniques. On a corpus of archives from the French monthly newspaper Le Monde Diplomatique, we obtain 40 classes of about 30 words each that accurately characterize precise topics, and allow us to detect their occurrences with a precision and recall of 85% and 65% respectively.

Keywords: topic detection, topic characterization, statistical data analysis, unsupervised classification

DOI: 10.3233/IDA-2005-9107

Journal: Intelligent Data Analysis, vol. 9, no. 1, pp. 105-127, 2005