2026-06-27T03:42:02Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/6295 2021-12-13T04:48:41Z 1582963342780:1605779935331 user-uit

Towards the Discovery of Genuine Social Groups from Mobility Data Htoo Htet Aung Nay Aung Lwin Phyo Phyo San Extraction of social groups from human mobility datasets has been regarded as convoy mining problem since a convoy (defined as a group of people which are spatially close to each other across time) is customarily assumed to represent a social group. However, social groups cannot be modelled trivially as a convoy as empirical evidence suggests convoy mining will report many ‘false positives’ and miss some ‘false negatives’. We propose a two-step method to discover social groups from human mobility data in real-time. To the best of our knowledge, this paper is the first attempt to discover genuine social groups from mobility data. Experiments on the real-life dataset indicate that our two-step approach can accurately and efficiently discover genuine social groups. 2018-11-02 http://hdl.handle.net/20.500.12678/0000006295 https://meral.edu.mm/records/6295