Title:	TOPIC MODELING OF TEXT CONTENT FOR MONITORING THE EMPLOYEE’S EFFICIENCY VIA HIS INTERNET ACTIVITY
Author(s):	Aleksandra Vatian, Sergey Dudorov, Artem Beresnev, Artem Vasilev, Niyaz Nigmatullin, Nikolay Vedernikov, Andrey Stankevich, Natalia Gusarova and Anatoly Shalyto
ISBN:	978-989-8533-80-7
Editors:	Ajith P. Abraham, Jörg Roth and Guo Chao Peng
Year:	2018
Edition:	Single
Keywords:	Topic Modeling, Regularization, Employee's Efficiency, Coherence, Portrait of Ideal Document
Type:	Full Paper
First Page:	43
Last Page:	50
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In this paper, we investigate the possibilities of topic modeling techniques, namely LDA and ARTM, for monitoring the employee’s efficiency via his Internet activity. Our experiments show that use of the ARTM model allows to construct the most accurate and well interpreted reference model of the information search. At the same time, if the employee begins to use inefficient scenarios of behavior, i.e. deviation or drift of information search, then it leads to deviations from the reference model, which can be identified by setting the cutoff threshold for concrete business. Our experiments show that the proposed solution provides a more confident identification of small deviations from the target topic in comparison with other methods, which is especially important in real business. The proposed model can find other applications, for example, parental control and highlighting the scientific articles related to the research topic.
	Go Back