We are in the midst of a technological revolution whereby, for the first time, researchers can link daily word use to a broad array of real-world behaviors. This article reviews several computerized ...text analysis methods and describes how Linguistic Inquiry and Word Count (LIWC) was created and validated. LIWC is a transparent text analysis program that counts words in psychologically meaningful categories. Empirical results using LIWC demonstrate its ability to detect meaning in a wide variety of experimental settings, including to show attentional focus, emotionality, social relationships, thinking styles, and individual differences.
Full text
Available for:
NUK, OILJ, SAZU, UKNU, UL, UM, UPUK
We develop and evaluate a real-time language feedback system that monitors the communication patterns among students in a discussion group and provides real-time instructions to shape the way the ...group works together. As an initial step, we determine which group processes are related to better outcomes. We then experimentally test the efficacy of providing real-time instructions which target two of these group processes. The feedback system was successfully able to shape the way groups worked together. However, only appropriate feedback given to groups that were not working well together from the start was able to improve group performance.
Collaborative problem solving Tausczik, Yla R.; Kittur, Aniket; Kraut, Robert E.
Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing,
02/2014
Conference Proceeding
The Internet has the potential to accelerate scientific problem solving by engaging a global pool of contributors. Existing approaches focus on broadcasting problems to many independent solvers. We ...investigate other approaches that may be advantageous by examining a community for mathematical problem solving -- MathOverflow -- in which contributors communicate and collaborate to solve new mathematical 'micro-problems' online. We contribute a simple taxonomy of collaborative acts derived from a process-level examination of collaborations and a quantitative analysis relating collaborative acts to solution quality. Our results indicate a diversity of ways in which mathematicians are reaching a solution, including by iteratively advancing a solution. A better understanding of such collaborative strategies can inform the design of tools to support distributed collaboration on complex problems.
In this paper we discuss a new methodology, social language network analysis (SLNA), that combines tools from social language processing and network analysis to assess socially situated working ...relationships within a group. Specifically, SLNA aims to identify and characterize the nature of working relationships by processing artifacts generated with computer-mediated communication systems, such as instant message texts or emails. Because social language processing is able to identify psychological, social, and emotional processes that individuals are not able to fully mask, social language network analysis can clarify and highlight complex interdependencies between group members, even when these relationships are latent or unrecognized.
Participation in an online mathematics community Tausczik, Yla R.; Pennebaker, James W.
Proceedings of the ACM 2012 conference on Computer Supported Cooperative Work,
02/2012
Conference Proceeding
Why do people contribute content to communities of question-answering, such as Yahoo! Answers? We investigated this issue on MathOverflow, a site dedicated to research-level mathematics, in which ...users ask and answer questions. MathOverflow is the first in a growing number of specialized Q&A sites using the Stack Exchange platform for scientific collaboration. In this study we combine responses to a survey with collected data on posting behavior on the site. User behavior suggests that building reputation is an important incentive, even though users do not report this in the survey. Level of expertise affects users' reported motivation to help others, but does not affect the importance of reputation building. We discuss the implications for the design of communities to target and encourage more contributions.
Researchers and theorists have proposed that feelings of attachment to subgroups within a larger online community or site can increase users' loyalty to the site. They have identified two types of ...attachment, with distinct causes and consequences. With bond-based attachment, people feel connections to other group members, while with identity-based attachment they feel connections to the group as a whole. In two experiments we show that these feelings of attachment to subgroups increase loyalty to the larger community. Communication with other people in a subgroup but not simple awareness of them increases attachment to the larger community. By varying how the communication is structured, between dyads or with all group members simultaneously, the experiments show that bond- and identity-based attachment have different causes. But the experiments show no evidence that bond and identity attachment have different consequences. We consider both theoretical and methodological reasons why the consequences of bond-based and identity-based attachment are so similar.
There are two perspectives on the role of reputation in collaborative online projects such as Wikipedia or Yahoo! Answers. One, user reputation should be minimized in order to increase the number of ...contributions from a wide user base. Two, user reputation should be used as a heuristic to identify and promote high quality contributions. The current study examined how offline and online reputations of contributors affect perceived quality in MathOverflow, an online community with 3470 active users. On MathOverflow, users post high-level mathematics questions and answers. Community members also rate the quality of the questions and answers. This study is unique in being able to measure offline reputation of users. Both offline and online reputations were consistently and independently related to the perceived quality of authors' submissions, and there was only a moderate correlation between established offline and newly developed online reputation.
Social language network analysis Scholand, Andrew J.; Tausczik, Yla R.; Pennebaker, James W.
Proceedings of the 2010 ACM conference on Computer supported cooperative work,
02/2010
Conference Proceeding
Open access
In this note we introduce a new methodology that combines tools from social language processing and network analysis to identify socially situated relationships between individuals, even when these ...relationships are latent or unrecognized. We call this approach social language network analysis (SLNA). We describe the philosophical antecedents of SLNA, the mechanics of preprocessing, processing, and post-processing stages, and the results of applying this approach to a 15-month corporate discussion archive. These example results include an explicit mapping of both the perceived expertise hierarchy and the social support / friendship network within this group.
