A user term visualization analysis based on a social question and answer log

  • Authors:

  • Jin Zhang;Yiming Zhao

  • Affiliations:

  • School of Information Studies, University of Wisconsin Milwaukee, Milwaukee, WI 53201, United States;Center for Studies of Information Resources, Wuhan University, Wuhan, Hubei Province 430072, PR China

  • Venue:
  • Information Processing and Management: an International Journal
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The authors of this paper investigate terms of consumers' diabetes based on a log from the Yahoo!Answers social question and answers (Q&A) forum, ascertain characteristics and relationships among terms related to diabetes from the consumers' perspective, and reveal users' diabetes information seeking patterns. In this study, the log analysis method, data coding method, and visualization multiple-dimensional scaling analysis method were used for analysis. The visual analyses were conducted at two levels: terms analysis within a category and category analysis among the categories in the schema. The findings show that the average number of words per question was 128.63, the average number of sentences per question was 8.23, the average number of words per response was 254.83, and the average number of sentences per response was 16.01. There were 12 categories (Cause & Pathophysiology, Sign & Symptom, Diagnosis & Test, Organ & Body Part, Complication & Related Disease, Medication, Treatment, Education & Info Resource, Affect, Social & Culture, Lifestyle, and Nutrient) in the diabetes related schema which emerged from the data coding analysis. The analyses at the two levels show that terms and categories were clustered and patterns were revealed. Future research directions are also included.