Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

COMPARATIVE ANALYSIS OF THE EFFICIENCY OF POPULAR ALGORITHMS FOR SEARCHING, ANALYZING, AND FILTERING INFORMATION USING INTELLIGENCE SYSTEMS

Gorbunov Konstantin Dmitrievich  (Postgraduate student, ITMO University)

Ivanov Sergey Evgenyevich  (Associate Professor, Candidate of Physical and Mathematical Sciences ITMO University )

Modern companies face the challenge of finding relevant instructions in their knowledge bases, resulting in the need to process a large number of incoming customer requests. This issue demands optimal solutions under limited IT resources and regulatory constraints. This article presents a comparative analysis of the performance of search and information filtering algorithms on small datasets within business constraints. The study compares algorithms such as TF-IDF, Bag of Words, Word2Vec, and FastText. The results of the conducted experiment demonstrated that the most efficient algorithm for small data samples is an improved TF-IDF algorithm, enhanced with text preprocessing functionality, hyperparameter optimization, and a hybrid approach incorporating KNN. The obtained results allowed for an increase in the accuracy of information retrieval without significant time loss. Thus, the proposed approach can be adapted to address a wide range of tasks in the field of text information processing.

Keywords:text processing, TF-IDF, Bag of Words, Word2Vec, FastText, search algorithms, machine learning, information filtering, small datasets.

 

Read the full article …

Citation link:
Gorbunov K. D., Ivanov S. E. COMPARATIVE ANALYSIS OF THE EFFICIENCY OF POPULAR ALGORITHMS FOR SEARCHING, ANALYZING, AND FILTERING INFORMATION USING INTELLIGENCE SYSTEMS // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2025. -№04. -С. 72-76 DOI 10.37882/2223-2966.2025.04.10
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences