Personal tools
User menu


From Computational CyberPsychology Lab

Jump to: navigation, search


Web Browsing Behavior and Mental Health

It is very important to detect web users’ mental health which can help people adjust their bad moods and live in this complicated internet world. Nowadays, web behavior plays a significant role in people’s life. It is widely accepted in clinical psychology that mental activities and statuses are expressed in a way of behavior such as preference and choice. Web behavior, as a part of behavior, is supposed to be a meaning to detect users’ mental status. In other words, individuals’ mental status or moods are showed in these details of Internet usage behavior. We apply machine learning methods to predict users' mental statuses and implement this system into a web browser--WebMind. WebMind first uses browsing behavior to predict users' psychological status and recommends some methods for whom in unstable mental status.

Weibo and Social Alarming System

Recently, China is in a transition of economy and society. Many potential social problems and social conflicts appear, which constitute social instability and bring threats and challenges to social stability and harmony. Our team propose to establish a social early alarming system based on a prediction model of users' social satisfaction. This model forecast users' social satisfaction using their web behavior in Sina Weibo.

Social Network and Personalities

Personality can be defined as a set of characteristics which make a person unique, and the study of personality is of central importance in psychology. Most personality-related research efforts rely on self-reported test using various inventories. One potential drawback is that respondents are possible to distort their responses, as only subjective validation is involved. Here, we propose a novel approach to predict the so called Big-Five Personality of a user from his/her Social Network Site(SNS) behaviors. This is the first attempt ever reported to measure the Big-Five Personality objectively. We collect users’ SNS behaviors and train a prediction model using machine learning methods. Different from the conventional inventory- based psychological analysis, our experimental studies predict users' personalities based on their online behaviors.

Mobile Usage and Mental Health

We present a psychological self-regulation research solutions based on cognitive behavioral therapy (CBT), design and implement SMS collection on the Android mobile terminal, psychological surveys and feedback application, psychological self-adjust service systems, etc.

Website:Mental Coach

This website helps people who are in pain of anxiety or depression. Using cognitive theory, this self-help adjust system leads people to recognize the right and wrong ideas.

Ontology of Web Behaviors

Ontology plays a significant role of specifying concepts in area of scientific investigation, including concepts sharing and clarification of relationship structure. As an extension of real-life behavior, in virtual environment, web usage behavior is almost the only valid indicator for predicting web user’s implicit psychological construct. Based on ontology of web usage behaviors, the relationship between web usage behavior and mental state would be confirmed and researcher could extract valid web behavior indicator purposely to predict web user’s state of mind instantaneously, objectively and accurately.

Multitask Learning

Multitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. It does this by learning tasks in parallel while using a shared representation; what is learned for each task can help other tasks be learned better.

  • This page was last modified on 24 August 2012, at 17:28.
  • This page has been accessed 7,893 times.