Presentation	2013-06-22 Social emotion estimation by analyzing tweets using latent Dirichlet allocation Masahiro OHMURA, Koh KAKUSHO, Takeshi OKADOME,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	The method proposed here analyzes the social sentiments from collected tweets that have at least one of 800 sentimental adjectives. By dealing with half-a-day tweets as a document, the method extracts the social sentiments using Latent Dirichlet Allocation (LDA). It captures some sentiments that match our daily sense, although some do not coincide with it. The extracted sentiments, however, indicate lowered sensitivity to changes in time. Using LDA for the representative 72 adjectives to which each of the 800 adjectives maps with preserving the word frequencies permits us to obtain sentiments that show improved sensitivity to changes in time.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	LDA / Topic modeling / Twitter / Sentiment analysis / Natural language processing
Paper #	DE2013-9
Date of Issue

Conference Information
Committee	DE
Conference Date	2013/6/15(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Data Engineering (DE)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Social emotion estimation by analyzing tweets using latent Dirichlet allocation
Sub Title (in English)
Keyword(1)	LDA
Keyword(2)	Topic modeling
Keyword(3)	Twitter
Keyword(4)	Sentiment analysis
Keyword(5)	Natural language processing
1st Author's Name	Masahiro OHMURA
1st Author's Affiliation	()
2nd Author's Name	Koh KAKUSHO
2nd Author's Affiliation
3rd Author's Name	Takeshi OKADOME
3rd Author's Affiliation
Date	2013-06-22
Paper #	DE2013-9
Volume (vol)	vol.113
Number (no)	105
Page	pp.pp.-
#Pages	6
Date of Issue