Re-Evaluation of On-Line Hot Topic Discovery Model

As a major medium for information transmission, Internet plays an important role in diffusing and spreading news on web. Some governments attach great importance and pay lot of effort trying to detect, track the development of events and forecast emergency on internet. On the basis of the researches in the field of topic detection and tracking, we proposed a model for hot topic discovery that would pick out hot topics by automatically detecting, clustering and weighting topics on the websites within a time period. We also introduced a topic index approach in following the growth of topics, which is useful to analyze and forecast the development of topics on web.