Sensing the world: Knowing Events and People’s Opinions using Social Media Analysis

On 11th March 2011, a 9.0-magnitude megathrust earthquake occurred in the ocean near Japan. This was the first large scale natural disaster in Japan since the broad adoption of social media tools (such as Facebook and Twitter). Since many people posted their own information to their followers in Twitter at that time, we could know what were happening in various areas from the tweets. Some people also posted tweets with their thought. In general, messages posted in Social Medias can be considered as a “sensor” of the world, not only sensing events but also sensing peoples’ opinions. Using Natural Language Processing, Network Analysis and/or other technologies, we can identify events and peoples’ thoughts in the world. In this talk I will show key technologies for social analytics and show some analysis results using these technologies for disaster managements, marketing, etc. I will also show the results of social analytics of candidates’/voters’ activities in the Net for the Japan House of Councilors election in July 2013.


Akiko Murakami is currently advisory researcher in Knowledge and Infrastructure group at IBM Research-Tokyo. Ms. Murakami joined IBM in 1999 as a researcher after received a Master’s degree in Applied Physics from Waseda University. Ms. Murakami’s research interests relate to the Natural Language Processing, especially for analysis of documents and activities in communication systems like Social Networking Services. Ms. Murakami also translated several technical books on Natural Language Processing and Information Retrieval into Japanese.