Open AccessDevelopment of Chatbots to Support Web Site Content Search Based on Thematic and Genre Characteristics
Author(s) -
V. D. Rublev,
Elena A. Sidorova
Publication year - 2022
Publication title -
vestnik novosibirskogo gosudarstvennogo universiteta. seriâ: informacionnye tehnologii/vestnik novosibirskogo gosudarstvennogo universiteta. seriâ: informacionnye tehnologii v obrazovanii
Language(s) - English
Resource type - Journals
eISSN - 2410-0420
pISSN - 1818-7900
DOI - 10.25205/1818-7900-2021-19-4-50-66
Subject(s) - computer science , structuring , information retrieval , world wide web , search engine , thematic map , cluster analysis , resource (disambiguation) , artificial intelligence , computer network , cartography , finance , economics , geography
The paper considers an approach to creating intelligent assistants in the form of chatbots that support information search based on preliminary genre and thematic clustering of website content. The tasks of finding the necessary in-formation and providing information support to the user, organizing feedback to improve the quality of the search are being solved. A feature of the approach is the use of genre models developed for a given type of resource (educational, informational, etc.), on the basis of which genre structuring of the content of a particular site is carried out. The resulting genre structures allow you to more accurately determine the boundaries of thematic clusters related to the topic of the user's search query. To provide feedback to the user, a simple script has been developed that allows not only to clarify the request, but also to implicitly get information about what exactly did not suit the user in the resulting out-put. An experimental study was conducted on the Telegram platform, the results were compared with the Yandex search engine.