Scalable Modeling of Conversational-role based Self-presentation Characteristics in Large Online Forums

نویسندگان

  • Abhimanu Kumar
  • Shriphani Palakodety
  • Chong Wang
  • Carolyn Penstein Rosé
  • Eric P. Xing
  • Miaomiao Wen
چکیده

Online discussion forums are complex webs of overlapping subcommunities (macrolevel structure, across threads) in which users enact different roles depending on which subcommunity they are participating in within a particular time point (microlevel structure, within threads). This sub-network structure is implicit in massive collections of threads. To uncover this structure, we develop a scalable algorithm based on stochastic variational inference and leverage topic models (LDA) along with mixed membership stochastic block (MMSB) models. We evaluate our model on three large-scale datasets, Cancer-ThreadStarter (22K users and 14.4K threads), Cancer-NameMention(15.1K users and 12.4K threads) and StackOverFlow (1.19 million users and 4.55 million threads). Qualitatively, we demonstrate that our model can provide useful explanations of microlevel and macrolevel user presentation characteristics in different communities using the topics discovered from posts. Quantitatively, we show that our model does better than MMSB and LDA in predicting user reply structure within threads. In addition, we demonstrate via synthetic data experiments that the proposed active sub-network discovery model is stable and recovers the original parameters of the experimental setup with high probability.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

L2 Learners’ Use of Metadiscourse Markers in Online Discussion Forums

This study aimed to investigate the use of interactional metadiscourse markers in 168 comments made by 28 university students of engineering via an educational forum held as part of a general English course. The students wrote their comments on six topics, with a total of 19,671 words. Their comments during educational discussions were analyzed to determine their use of five metadiscourse categ...

متن کامل

The Relationship between Self-esteem and Conversational Dominance of Iranian EFL Learners’ Speaking

The crucial role of affective factors like anxiety, inhibition, motivation and self-esteem have long been of interest in the field of language learning due to their enormous association with the cognitive processes involved in performance in a second or foreign language. This study aimed at investigating the relationship between Iranian EFL learners’ self-esteem and conversational dominance in ...

متن کامل

The Presentation of Self in a Virtual but Work-related Environment

More and more people take part in virtual environments in which they present a “virtual self”—an online profile that indicates key information about them to other participants and viewers. This research investigates how people present themselves in the virtual yet work-related environments of occupational online forums. To do so, the research analyzes the profiles of more than 300 registered us...

متن کامل

Teens, Gender, and Self-Presentation in Social Media

This chapter is concerned with how teenage boys and girls present themselves through online social media such as Facebook, Twitter, blogs, and chat forums. Based on research conducted mostly in the United States, it describes and considers the implications of social media use, profile construction, visual and textual self-presentation, profile visibility, truthfulness, and other facets of teens...

متن کامل

Triaging Content Severity in Online Mental Health Forums

Mental health forums are online communities where people express their issues and seek help from moderators and other users. In such forums, there are often posts with severe content indicating that the user is in acute distress and there is a risk of attempted self-harm. Moderators need to respond to these severe posts in a timely manner to prevent potential selfharm. However, the large volume...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1512.03443  شماره 

صفحات  -

تاریخ انتشار 2015