The Smart-TSH-Finder: Crawling and Analyzing Tempo-Spatial Hotspots in Second Life

In this paper we introduce the Smart Tempo-Spatial Hotspots Finder (Smart-TSH-Finder) for smart data crawling in the Second Life (SL) virtual world. Classical methods of crawling data from SL lead to irrelevant data content because of the dynamic nature of avatars and objects in SL. In order to build artificially intelligent expert avatar agents that are able to provide intelligent services for other typical avatars in virtual world we attempt to enhance the quality of extracted data from SL. Based on experimental observation, avatars tend to gather in some places for different amounts of time, which forms temporal and spatial hotspots. Utilizing the Tempo-Spatial characteristics of the avatars behavior in virtual worlds could improve the quality of the extracted data. Smart-TSHFinder implements a Tempo-Spatial Hotspots finding mechanism to crawl dynamic contents such as chat conversations from Second Life. The system introduces two mechanisms: the Tempo-Spatial Hotspots Detection, and the Tempo-Spatial Hotspots Prediction. Our smart chat conversations that have been crawled showed good enhancement in content quality of the crawled chat conversation which will enrich the future textual analysis work. Additionally, we found that extracting avatars interactions and behavior in the Tempo-Spatial Hotspots in addition to chat conversations can help in generation a more coherent social network model for SL.