Open AccessChatbot for Monitoring Mental Health and Personality Trait Identification
Author(s) -
J.Monisha Privthy Jeba,
S. Bharath,
P. Gowtam,
G. Praveen
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.h7160.078919
Subject(s) - feeling , chatbot , psychology , trait , identification (biology) , computer science , process (computing) , classifier (uml) , personality , big five personality traits , sentiment analysis , security token , applied psychology , social psychology , artificial intelligence , computer security , botany , biology , programming language , operating system
AI Chabot or conversational agents are application that mimics human communication. They can entertain, motivate and actively engage people. An important concern faced by most people is stressed disorders. These disorders can include OCD and posttraumatic stress disorders. Most affected category of people is the employees and students. In order to prevent this, counseling is provided. It is done by the HR managers in IT companies and by the teachers to the students or by professionals. But most people are not open to the specialists and feel more uncomfortable during this process of expressing their feelings. This process can be made simple by using a Chatbot. This Chatbot communicates with the people, identifies their traits and provides their sentiment scores to an authorized person. There are three key modules in the development process. First is the Sequence-to-Sequence model. This model consists of an encoder and a decoder. The received input text is converted to tokens and each token is identified with a random number, which is common for the same tokens. The second module is the sentiment analysis which is used in identifying the emotions of a person. The sentiment score is generated for the users. The traits of the person are identified from the chat logs. A RNN (Recurrent Neural Network) is built to identify the trait of the person from the pre-defined 16 types of personality traits. The multi-class classifier’s output can be combined with the sentiment score to truly identify the characteristics of the users.