DocumentCode :
1910609
Title :
A Motif Approach for Identifying Pursuits of Power in Social Discourse
Author :
Bracewell, David B. ; Tomlinson, Marc ; Wang, Hui
Author_Institution :
Language Comput. Corp., Richardson, TX, USA
fYear :
2012
fDate :
19-21 Sept. 2012
Firstpage :
1
Lastpage :
8
Abstract :
In this paper, we investigate whether the social goals of an individual´s utterances can be recognized through analysis of a discourse´s intentional structure. Specifically we focus on identifying individuals pursuing power within a group. Individuals pursue power in order to increase their control of the actions and goals of the group. Following work in discourse processing we decompose the problem into identifying the social intention of the discourse segments and the intentional structure of the overall discourse. The set of social intentions come from eight psychologically-motivated social acts. We then build a motif-based representation of the discourse´s social intentional structure that captures the interactions of the intentions between discourse participants. Finally we show how these structures can be used to identify the social goal of pursuit of power. Our best results achieve an accuracy of 84.2% for predicting pursuit of power in discussions communicated in English and 80.6% for discussions communicated in Chinese.
Keywords :
natural language processing; social sciences computing; user interfaces; Chinese; English; discourse intentional structure analysis; discourse processing; discourse segments; motif-based representation; power pursuit identification; psychologically-motivated social acts; social discourse; social goals; social intention identification; social media; Blogs; Color; Iterative closest point algorithm; Media; Pragmatics; Semantics; Social network services;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Semantic Computing (ICSC), 2012 IEEE Sixth International Conference on
Conference_Location :
Palermo
Print_ISBN :
978-1-4673-4433-3
Type :
conf
DOI :
10.1109/ICSC.2012.22
Filename :
6337148
Link To Document :
بازگشت