Associated Keyword analysis for temporal data with spatial visualization

Abstract

To extract temporal variations in the relation between two or more words in a large time-series script, we propose three procedures for adoption by the existing Associated Keyword Space system, as follows. First, we begin the calculations from a previous state. Second, we add a random seed if a new object was present in the previous state. Thrid, we forget those object relations from the previous state that have no affinity with the selected term. We have experimented with this improved algorithm using a large time-series of tweets from Twitter. With this approach, it is possible to check on the volatility of topics.