UDC 615.47
CLASSIFIER FOR EVALUATING PREDICTION BY THE USER OF HIERARCHICAL TEXT MENUS ON «LIKE / DISLIKE» SCALE
A. N. Varnavsky, PhD (technical sciences), assistant professor, RSREU, Ryazan; This email address is being protected from spambots. You need JavaScript enabled to view it.
M. V. Goubko, PhD (physics and mathematical sciences), Leading Researcher, the Institute of Management Problems named after Trapeznikov , Moscow; This email address is being protected from spambots. You need JavaScript enabled to view it.
The article is the result of building a classifier to predict the evaluation made on «like / dislike» scale by the user of hierarchical text menus. The aim of work is to research the influence of structural parameters of hierarchical text menus and individual psycho-physiological characteristics of user's satisfaction with user experience with menu and to build the classifier based on the results of study. An experiment in which participants worked with 10 different developed hierarchical text menus and then evaluated the usability of each menu on «like / dislike» scale is made. Also, the subjects were psycho-physiological testing. On the basis of experimental data the classifier was built, i.e. logistic regression to assess whether the user likes the menu with set parameters of specific values of memory performance, attention and level of logical thinking. The resulting model allows us to classify correctly 78% of various menus estimates. The results can be used in the development of hierarchical text menus for various programs.
Key words: hierarchical text menus, menu options, user performance, psychophysiological testing, memory performance and attention level of logical thinking, «like / dislike» evaluation, logistic regression.