Deliverable D3.2 “Development of accurate and sophisticated sentiment analysis approaches”

This deliverable, D3.2 “Development of accurate and sophisticated sentiment analysis approaches”,refers to the activities that were carried out as part of tasks 3.2 and 3.3 of the Work Package 3 (WP3) of the ENCASE project.

The purpose of Task 3.2 was to study ways to improve user experience and user behavior when faced with security and privacy risks. The usability and user-experience of existing security and privacy systems for OSNs has been evaluated using query based techniques (questionnaires, interviews, focus groups) and through usability studies (observations, eye-tracking studies).

The purpose of Task 3.3 was to complement the user studies from T3.2 with sentiment analysis of OSN content. The understanding of how people feel about things they are talking about, needs the development of accurate and sophisticated sentiment analysis approaches. Existing challenges, such as the recognition of sarcastic or ironic content, should be addressed for a successful capturing ofpeople’s sentiments. The adoption of such approaches can contribute in solving important openissues (e.g. the timely recognition of people with suicidal tendencies or criminal behavior) and can significantly contribute to the identification and management of critical situations.

A long literature review has been conducted regarding sentiment analysis and articles related to Twitter analysis were recorded and analysed in order to investigate the basic principles of Twitter operation and to compare their outcomes with our own first findings. A statistical analysis ofOSWINDS’ dataset was conducted and a report that sums up our findings is included in this deliverable.

Furthermore, developments on the parental console regarding the traffic blocking options are presented in this deliverable as well.