Situating Big Data: Assessing Game-Based STEM Learning in Context

Principal Investigator: 
Project Overview
Background & Purpose: 

This project seeks to marry theories of situated cognition to the big data movement by connecting clickstream data exhaust from learning technologies (here, specifically games) to key forms of discourse data available from their contexts of use (social interaction and texts) in a theoretically principled and empirically validated manner.

Setting: 

An after school game-based program in the Midwest.

Research Design: 

The project will generate evidence that is descriptive [case study, telemetric analyses, natural language processing, discourse analyses]. Original data are being collected on 7th and 8th graders using assessments of learning, observation [personal observation, videography, Web logs], survey research [self-completion questionnaire, semi-structured or informal interview, focus groups], and other sources including telemetric data exhaust from game technology, online forum posts, and face-to-face interaction. Instruments or measures being used include diagrams of cellular structures and functions, pre/posttests of knowledge comprehension, and gameplay levels.

In addition to basic pre/post assessments of learning, we will combine three forms of analysis of the data and look for patterns of relationship across them: (1) educational data mining and learning analytics on telemetric data from the game platform, (2) discourse analysis and human coding of online and face-to-face discourse data, (3) natural language processing of online and face-to-face discourse data.

Findings: 

Findings will be posted as they become available.

Other Products: 

Data architecture to integrate discourse data with telemetric data.