期刊名称：Eastern-European Journal of Enterprise Technologies
印刷版ISSN：1729-3774
电子版ISSN：1729-4061
出版年度：2016
卷号：5
期号：2
页码：4-12
DOI：10.15587/1729-4061.2016.77174
语种：English
出版社：PC Technology Center
摘要：The approach is proposed to developing an information system of determining the psychological state of personalities based on the five personality dispositions (extraversion/introversion, amiability, integrity, neuroticism, openness to experience), which is based on the content analysis of the Internet resources where users leave their mark (social networks, forums, chats, etc.).In general, to form the status of psychological state of a personality based on the content analysis, it is necessary to solve four problems. First, it is necessary to collect content from various sources from the Internet. Then it is necessary to process it at the initial level (remove the tags, auxilary words, signs, special symbols, hyperlinks, pictures, etc. from the text). Then the content is filtered (to identify spam, detect duplication, format the content, etc.) and sorted out (comments to the comments, likes, posts) according to the statistics over a specific period. The last stage is conducting the content analysis of collected information, which is categorized by the stop-words (markers).To determine the psychological dispositions of a personality we implemented the developed method of the search and analysis of the marked words in the English and Ukrainian languages. We used the Potter stemming, lemmatising and the modified Potter stemming for the Ukrainian texts, designed by the authors. The tables of correlation between the marked words and psychological dispositions were developed. The information system is created for determining the psychological state of personality, based on the developed approach and the methods of the content processing. The system operates by analyzing the messages from the users in a social network based on the traits of the "Big Five". The system is designed in the form of a desktop program, which is the Internet service at the same time, and allows analyzing the psychological state of a particular user of a social network by his/her messages. All collected results are stored in the database. The results are displayed in the form of percent ratio for each trait, the number of tweets, as well as the most frequently used words related to these traits.Potential users of such systems are consulting and marketing companies. The collected and analyzed information on users may be used in hiring or promotion of products/services. Automated compilation of the personality models of users is helpful for social networks and Web services. It improves the quality and efficiency of context advertising, referral systems, recommendations and dating services. The in-depth knowledge of the audience is crucial for business and recruiting.The approbation of functioning of the constructed system was conducted. The results of the work of the system are satisfactory. Such an information system is recommended to use for searching employees for certain positions.Automated analysis of messages of users in a social network to form the status of psychological state of a personality based on the content analysis significantly reduces the time of finding a potentially promising employee among those applied taking into account his/her psychological portrait for a specific position.
