The accuracy of keyword extraction is a leading factor in marketing and information management. In the present study, the available information of all languages is used simultaneously to improve keyword extraction in a multilingual text, such that a word is selected as the keyword of a text in a certain language that in addition to that language holds a high rank based on the keywords criteria in other languages, as well. Thus, that a word has the keyword criteria only in one language not in other languages may not qualify it as a keyword. This could decrease the percentage of false keywords and increase the accuracy of an algorithm. The obtained results indicated that algorithm accuracy of the multilingual texts in term frequency- inverse document frequency (TF-IDF) algorithm, graph-based algorithm, and the improved proposed algorithm is 80%, 60.65%, and 91.3%, respectively.
پیوند مجله / همایش