Extended list of stop words: Does it work for keyphrase extraction from short texts?

In this paper we study the problem of key phrase extraction from short texts written in Russian. As texts we consider messages posted on Internet car forums related to the purchase or repair of cars. The main assumption made is: the construction of lists of stop words for key phrase extraction can be effective if performed on the basis of a small, expert-marked collection. The results show that even a small number of texts marked by an expert can be enough to build an extended list of stop words. Extracted stop words allow to improve the quality of the key phrase extraction algorithm. Prior, we used a similar approach for key phrase extraction from scientific abstracts in the English language. In this paper we work with Russian texts. The obtained results show that the proposed approach works not only for texts that are appropriate in terms of structure and literacy, such as abstracts, but also for short texts, such as forum messages, in which many words may be misspelled and the text itself is poorly structured. Moreover, the results show that proposed approach works well not only with English texts, but also with texts in the Russian language.