跳到主要內容區

103/12/18(四) Location and Language Use in Social Media

國立清華大學資訊工程學系

Department of Computer Science

National Tsing Hua University

專題演講

SEMINAR

主講人Ed Chi ( Staff Research Scientist, Google )

SPEAKER

題 目 Location and Language Use in Social Media

TOPIC

時  間103 年 12月 18日 (四) 下午 3:30 - 5:00

DATE

地 點台達 109    

PLACE             

Abstract:

We now know that social interactions are critical in many knowledge and information

processes. In this talk, I plan to illustrate a model-driven approach to understanding

social behavior around user location and different languages in social media. 

 

First, in 2010, we performed the first in-depth study of user location field in Twitter

user profiles. We found that 34% of users did not provide real location information,

frequently incorporating fake locations or sarcastic comments that can fool traditional

geographic information tools. We then performed a simple machine learning experiment

to determine whether we can identify a user’s location by only looking at contents of a

user's tweets. We found that a user’s country and state can in fact be determined easily

with decent accuracy, indicating that users implicitly reveal location information, with or

without realizing it.

 

Second, despite the widespread adoption of Twitter in different locales, little research

has investigated the differences among users of different languages. In prior research,

the natural tendency has been to assume that the behaviors of English users generalize

to other language users. We studied 62 million tweets collected over a four-week period.

We discovered cross-language differences in adoption of features such as URLs, hashtags,

mentions, replies, and  retweets.

We also found interesting patterns of how multi-lingual Twitter users broker information

across these language boundaries. We discuss our work's implications for research on

large-scale social systems and design of cross-cultural communication tools.

 

                                                                                                                                                                       聯絡人:王浩全教授

瀏覽數:
登入成功