Posted on July 3, 2017

This tool was developed to aid an Alzheimers content analysis study. Building the tool involved scrapping over 400,000 posts and related user data from the ALZConnected.org website using scrappy. A subset of 3,000 posts and replies were then extracted randomly from the scrapped data using custom scripts for categorization by the investigators and stored in a MySQL database. The web based categorization tool developed allows multiple users to categorize the 3,000 posts independent of each other. The categories used for the posts had a hierarchical structure with 3 levels. The selected categories on multiple levels were all stored in the database on a per user basis.The per used categorized data was then collated to calculate metrics for categorization and investigate the content.

Further details of the study can be found in the published article below.

• Scharett, E., Lopes, S., Rogers, H., Bhargava, A., Madathil, K. C., Dye, C. (2017). “An Investigation of Information Sought by Caregivers of Alzheimers Patients on Online Peer-Support Groups through a Content Analysis of ALZConnected.org A Pilot Study”, accepted in the proceedings of Human Factors and Ergonomics Society