Temporal awareness of changes in afflicted people´s needs after East Japan Great Earthquake

This paper proposes a time series topic detection method to investigate changes in afflicted people´s needs after the East Japan Great Earthquake using latent semantic analysis and singular vectors´ pattern similarities. Our target data is a blog about afflicted people´s needs provided by a non-profit organization in Tohoku, Japan. The method crawls blog messages, extracts terms, and forms document-term matrix over time. Then, it adopts the latent semantic analysis to extract people´s needs as hidden topics from each snapshot matrix. We form time series hidden topic-term matrix as 3rd order tensor, so that changes in topics (people´s needs) are detected by investigating time-series similarities between hidden topics. In this paper, to show the effectiveness of our proposed method, we also provide the experimental results.