Detecting the Mobility of Patient with Chronic Diseases in Online Health Communities using Ant Colony Optimization Algorithm Ensure Patient’s Safety and Diseases Awareness based on Reliable Medical Education Material

The importance of online health communities (OHCs) is evidenced by their popularity, as well as how they significantly impact the live style of their members. Like other social media platforms, OHCs also face, however, exodus problems where community's members are most often moving from one community to another looking for answers to their concerns. This phenomenon is especially more noticeable in online health communities. Community's members are connected to each other through the online discussion topics and subtopics. Since community's members are moving from one community to the other and back, it is matter for example for the public health care system bodies to follow the movement of the health care services consumers or potential patients on the internet and, thus, determine their topics of interest with the objective to verify the information disseminated within these communities and act in the case of dissemination of wrong or life threating information. The final objective could be the improvement of the patient education material disseminated on the internet. To investigate patient's behaviors and identify the information they are searching for and consuming on the internet, the ant colony optimization algorithm is used to detect their movements and topics of interest. Ant colony optimization algorithm (ACOA) is a probabilistic technique for solving computational problems which can be reduced to finding good paths through graphs. A community can be represented as a graph where the vertices represent the members and the edges le topics connecting members. The results of the conducted experiments shown that the proposed mobility model is more efficient, accurate, precise, and realistic than the common random mobility models. Furthermore, the test revealed a socialization enhancement as a benefit for the patient.