Enhanced Reputation-based Tit-for-Tat Strategy for Collaborative Social Applications

Abstract

Social applications have witnessed a rapid growth in their use. Millions of people are utilizing them on a daily basis in order to share their experience, information and to communicate with their family members and friends. Lately, these technologies have been used to foster collaboration in education, however, it is a case of hit and miss and without established techniques to ensure or replicate success. One known problem that can impact the sustainability of collaborative social applications is the presence of selfish users. A selfish user adopts a free riding behaviour that takes advantage of the collaborative group without contributing back which would affect the group’s survivability. However, the inability to contribute back is not necessarily due to selfishness. In fact, cooperative learners may avoid participating due to the lack of expertise and/or confidence. In the literature, repeated non-cooperative game theory was introduced as a solution where several strategies were introduced to identify selfish users. However, such strategies do not differentiate between selfish learners and cooperative learners who are reluctant to answer others’ requests either due to lack of knowledge or confidence. In this paper, we show that educational and collaborative groups need to distinguish between those types of users and put in place mechanisms to encourage non contributing cooperative learners to participate rather than punishing them and excluding them from the group. An enhanced reputation-based Tit-for-Tat strategy is proposed as a solution that will enhance the group activity and overall gain.