Using Keystroke Dynamics in a Multi-Agent System for User Guiding in Online Social Networks

Guillem Aguado,Ana García-Fornes,Vicente Julián,Agustín Espinosa

doi:10.3390/app10113754

Abstract

Nowadays there is a strong integration of online social platforms and applications with our daily life. Such interactions can make risks arise and compromise the information we share, thereby leading to privacy issues. In this work, a proposal that makes use of a software agent that performs sentiment analysis and another performing stress analysis on keystroke dynamics data has been designed and implemented. The proposal consists of a set of new agents that have been integrated into a multi-agent system (MAS) for guiding users interacting in online social environments, which has agents for sentiment and stress analysis on text. We propose a combined analysis using the different agents. The MAS analyzes the states of the users when they are interacting, and warns them if the messages they write are deemed negative. In this way, we aim to prevent potential negative outcomes on social network sites (SNSs). We performed experiments in the laboratory with our private SNS Pesedia over a period of one month, so we gathered data about text messages and keystroke dynamics data, and used the datasets to train the artificial neural networks (ANNs) of the agents. A set of experiments was performed for discovering which analysis is able to detect a state of the user that propagates more in the SNS, so it may be more informative for the MAS. Our study will help develop future intelligent systems that utilize user data in online social environments for guiding or helping them in their social experience.

Highlights

The presence of online applications in our daily lives has risen recently, and social network sites (SNSs) are some of the most predominant
There were cases that provided a network that was very likely to give as output one of the two classes. This was because the data in the partition of the dataset used for the experiment were unbalanced in favor of one of the classes, which resulted in high propagation in the later experiment
We introduced new agents capable of performing sentiment and stress analysis on keystroke dynamics data into a multi-agent system (MAS) presented in a previous work, in order to improve the capacity of the MAS when predicting user states that could generate a problem or make risks arise from the social interaction

Summary

Introduction

The presence of online applications in our daily lives has risen recently, and social network sites (SNSs) are some of the most predominant. In this scenario, it is interesting that the systems that are managing online sites could help prevent potential issues that could arise from user interactions. There are contact risks or the risk of interacting with strangers, content risks or the risk of receiving inappropriate content, and commercial risks or the risk of being asked for personal information Another factor is the fact that certain social groups can be more vulnerable to risks. In [3] it is shown that teenagers, who belong to a social group that uses SNSs frequently [4], have characteristics that make them more vulnerable to risks navigating

Objectives

Methods

Results

Conclusion