Improving the search for information from Kazakh-language content in search systems

2024

Closed access Metadata (CSL-JSON)
DOI 10.1109/mosicom63082.2024.10881622
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The presented paper is devoted to exploring the ways to enhance the possibility of finding Kazakh-language text in search engines and improve the quality of search results. There have not been many studies conducted on data retrieval in the Kazakh language, and major search engines do not prioritize processing languages with small audiences, such as Kazakh. During the study, an analysis was conducted on the search results for Kazakh-language data in two search engines frequently used in Kazakhstan: google.kz and yandex.ru. The analysis revealed that these search engines are unable to sufficiently process textual data in Kazakh. To address this issue, the study proposed utilizing morphological analysis and identifying basic forms of searching words. Further, a test search engine was developed taking into account the identified shortcomings, and its results were compared with the results of other search engines.