Classification of Medical Online Helpdesk Users Solomiia Fedushko [0000-0001-7548-5856], and Yuriy Syerov [0000-0002-5293-4791] Lviv Polytechnic National University, Lviv, Ukraine solomiia.s.fedushko@lpnu.ua, yurii.o.sierov@lpnu.ua Abstract. Medical online help desk is authoritative and popular service for the online communication concerning medical issues. In critical situations people often rely on online services to get medical-related information and answers. Because of the possible risks, it is highly important that they do not receive or use false information. That’s the reason to filter false, unreliable or commercial information and discover forum-users that provide such information. On the other hand it would be positive thing to determine users that give competent and adequate advices. Such users’ classification will help online community’s ad- ministration to moderate community and will help users to get correct infor- mation. This method of classification of medical online help desk users was tested on medical online communities. Keywords: Help Desk, Medical-Related Information, Medical Online Com- munities, Users’ Classification, Medical Online Helpdesk. 1 Introduction In critical situations people often rely on online services to get medical-related in- formation and answers. Because of the possible risks, it is highly important that they do not receive or use false information. That’s the reason to filter false, unreliable or commercial information and discover forum-users that provide such information. On the other hand it would be positive thing to determine users that give competent and adequate advices. 48% internet users trust the information that is posted in a web- community. 2 Research Aims  develope the method of classification of medical online help desk users  determine medical online helpdesk users that give competent and adequate advices  method of classification of medical online help desk users tested on medical online communities Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons Li- cense Attribution 4.0 International (CC BY 4.0) IREHI 2018 : 2nd IEEE International Rural and Elderly Health Informatics Conference 2 3 Classes of Medical Online Helpdesk Users The membership of the users in one of the 5 classes: Patient, Professional, Disrup- tive, Medic, Critic, Reader. Such users’ classification will help medical online community’s administration to moderate community and will help users to get correct information. This method of classification of medical online help desk users was tested on medical online commu- nities. The development of methods for behavioral classification of users of medical online helpdesk in the scheme is presented. Modern research on social processes in the WWW covers the following areas are: users’ needs satisfaction, communication systems and formation and management of medical online helpdesk. Fig. 1. Classes of Medical Online Helpdesk Users 3 4 Fuzzy Logic Approach Data fusion techniques, namely fuzzy logic, are employed to process the captured data to increase the trust level of classification. Fuzzy logic has been used in applica- tions that are amenable to conventional control algorithms on the basis of mathemati- cal models of the system being controlled. However, fuzzy logic has a particular ad- vantage in areas where precise mathematical description of the control process is impossible and is thus especially suited to support medical decision making. A fuzzy logic–based approach to the automatic classification of helpdesk users. Fuzzy logic plays an important role in some medicine areas is developed. For example:  To predict the response to have treatment with citalopram in alcohol depend- ence;  To analyze diabetic neuropathy;  To detect early diabetic retinopathy;  To improve decision-making in process  low medium high 1 0,5 x P1 , P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 , P12 Fig. 2. Fuzzy Logic Approach 4 5 Rules for Classifying Medical Online Helpdesk Users The membership of the users in one of the classes (Patient, Professional, Disrup- tive, Medic, Critic, Reader) based on its characteristics (Activity, Creativity, Attrac- tion, Reactivity, Loyalty) is represented by production rules and table. It is important to determine the characteristics of medical online helpdesk users at the thematic level of the entire helpdesk. 5 6 Algorithm of Classifying Medical Online Helpdesk Users Fig. 3. Algorithm of Classifying Medical Online Helpdesk Users 6 7 Entity Relationship Diagram of Medical Online Helpdesk Fig. 4. Entity Relationship Diagram of Medical Online Helpdesk 8 Sheme of the Classifying Users in Medical Online Helpdesk Available research methods are reduced to a fragmentary solution to the problem, they are theoretical and the results of these studies are mostly not tested in practice. 7 Fig. 5. Sheme of the Classifying Users in Medical Online Helpdesk 9 Results of Classification Medical Online Helpdesk Users So, we set the main characteristics of the users within the entire helpdesk. Defining these characteristics allows users to classify the user of medical online helpdesk and based on this classification, build community management methods and algorithms to remove unwanted helpdesk users from the creators, which will ensure its improve- ment. Fig. 6. Results of Classification Medical Online Helpdesk Users 8 The key idea of this study is modelling the behavior classification of users of med- ical online helpdesk by using fuzzy logic approach. Implantation of mathematical concepts based on fuzzy logic is a solution to complex problems in all areas of sci- ence as it method of human reasoning and decision making. The fuzzy logic approach is acceptable for the problems that required high accuracy. Conclusion Developed methods for determining the main characteristics of the users of the medical online helpdesk:  professionalism;  reputatitiveness;  attractiveness;  reactiveness;  activeness. The classes of users of medical online helpdesk are allocated and the rules of clas- sification of users are formulated. References 1. Fedushko S., Shakhovska N., Syerov Yu. Verifying the medical specialty from user profile of online community for health-related advices. CEUR Workshop Proceedings. Vol. 2255: Proceedings of the 1st International workshop on informatics & Data-driven medicine (IDDM 2018) Lviv, Ukraine, November 28–30, 2018. P. 301–310. 2. Fedushko S., Syerov Yu. Classification of Medical Online Helpdesk Users. IREHI 2018. http://ieee-rural-elderly-health.com/2018/wp-content/uploads/2018/12/IREHI-Programm- 1.pdf 3. Shakhovska, N., Vovk, O., Kryvenchuk, Y.: Uncertainty reduction in Big data catalogue for information product quality evaluation. Eastern European Journal of Enterprise Tech- nologies, Volume 1, Issue 2-91, 12-20 (2018). 4. Vitek, C. R. R., Nicholson, W. T., Schultz, C., Caraballo, P.: Evaluation of the use of clin- ical decision support and online resources for pharmacogenomics education. Phar- macogenomics, 16(14), 1595-1603 (2015). 5. Qassas, M. A., & et al.: ArgMed: A Support System for Medical Decision Making Based on the Analysis of Clinical Discussions. Real-World Decision Support Systems. Integrated Series in Information Systems, vol 37. Springer, pp. 15–41 (2016).