Sign inSign up
People on Drugs: Credibility of User Statements in Health Communities thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

People on Drugs: Credibility of User Statements in Health Communities

Published on Oct 08, 20142139 Views

Subhabrata Mukherjee

Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we

Research Sessions

Related categories

Data MiningKnowledge Extraction

Chapter list

People on Drugs : Credibility of User Statements in Health Forums00:00
Motivation: Internet as a healthcare resource - 100:10
Motivation: Internet as a healthcare resource - 200:43
Posts from Healthboards.com - 100:48
Posts from Healthboards.com - 201:14
Our Intuition - 101:44
Our Intuition - 203:25
Language: Stylistic Features - 103:34
Language: Stylistic Features - 203:51
Language: Stylistic Features - 303:56
Language: Stylistic Features - 404:00
Language: Stylistic Features - 504:04
Language: Stylistic Features - 604:12
Language: Stylistic Features - 704:24
Language: Stylistic Features - 804:36
Language: Objectivity04:51
Our Intuition - 305:28
User Features05:33
Objective06:18
Probabilistic Inference: CRF06:37
Semi Supervised Learning07:30
Semi-Supervised CRF (Sketch) - 108:46
Semi-Supervised CRF (Sketch) - 209:00
Semi-Supervised CRF (Sketch) - 309:10
Semi-Supervised CRF (Sketch) - 409:18
Semi-Supervised CRF (Sketch) - 509:31
Semi-Supervised CRF (Sketch) - 609:44
Semi-Supervised CRF (Sketch) - 710:06
Semi-Supervised CRF (Sketch) - 811:01
Semi-Supervised CRF (Sketch) - 911:09
Semi-Supervised CRF (Sketch) - 1011:22
Semi-Supervised CRF (Sketch) - 1111:31
Semi-Supervised CRF (Sketch) - 1211:49
Dataset - 111:54
Dataset - 212:06
Drug Statistics12:19
Baselines12:41
Accuracy Comparison13:15
Use-Case: Following Trustworthy Users13:29
Use-Case: Following Trustworthy Users14:18
Conclusions14:45