Temporal Awareness of Changes in Afflicted People’s Needs after East Japan Great Earthquake
IEEE TENCON 2013——This talk 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 talk, to show the effectiveness of our proposed method, we also provide the experimental results.
关键词: 时间序列 奇异向量 东日本大地震 受灾群众需求 IEEE TENCON 2013
主讲人:Associate Pro Takako Hashimoto 机构:Commerce and Economics Chiba University of Commerce
时长:0:14:31 年代:2013年
热点排行
- 1 揭开土豆减肥的秘密
- 2 英语学习策略(1)
- 3 古兽重现
- 4 《图书馆与信息服务营销》先导片
- 5 Excel实战技巧精粹
- 6 恐龙绝灭与生态危机(1)
- 7 在路上
- 8 生物医学图像处理——绪言(1)