Understanding user intents in online health forums

Online health forums provide a convenient way for patients to obtain medical information and connect with physicians and peers outside of clinical settings. However, the large quantities of unstructured and diversified content generated on these forums make it difficult for users to digest and extract useful information. Understanding the intents of people who post on these forums would enable the retrieval of relevant information from existing threads which would in turn allow users to more effectively find answers to their medical needs. In this paper, we derive a taxonomy of intents to capture user information need in online health forums, and propose novel pattern based features to classify original thread posts according to their underlying intents. Since no dataset existed for this task, we employ three annotators to manually tag a dataset of 1,200 HealthBoards posts spanning four topics. Experimentation finds that pattern based features are highly capable of identifying user intents in forum posts, reaching a precision of 75\%. In addition, we achieve comparable classification performance by training and testing on posts from different forums, thereby showing the robustness of our method. Finally, we run our trained classifier on a MedHelp dataset to analyze the distribution of intents of different topics in the forum.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2014

Author dc:creator

• Zhang, Thomas

Contributors dc:contributor

• Zhai, ChengXiang

• Intent Classification
• Forum Intents
• Health Forums

Statement dc:rights

• Copyright 2014 Thomas Qian-Yun Zhang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/50426

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/50426