TY - GEN
T1 - Using text replay tagging to produce detectors of systematic experimentation behavior patterns
AU - Sao Pedro, Michael A.
AU - Baker, Ryan S.J.D.
AU - Montalvo, Orlando
AU - Nakama, Adam
AU - Gobert, Janice D.
PY - 2010
Y1 - 2010
N2 - We present machine-learned models that detect two forms of middle school students' systematic data collection behavior, designing controlled experiments and testing the stated hypothesis, within a virtual phase change inquiry learning environment. To generate these models, we manually coded a proportion of the student activity sequence clips using "text replay tagging" of log files, an extension of the text replay method presented in Baker, Corbett & Wagner (2006). We found that feature sets based on cumulative attributes, attributes computed over all predecessor clips, yielded better detectors of CVScompliant and hypothesis-testing behavior than more local representations of student behavior. Furthermore, our detectors classify behaviors well enough to use them in our learning environment to determine which students require scaffolding on these skills.
AB - We present machine-learned models that detect two forms of middle school students' systematic data collection behavior, designing controlled experiments and testing the stated hypothesis, within a virtual phase change inquiry learning environment. To generate these models, we manually coded a proportion of the student activity sequence clips using "text replay tagging" of log files, an extension of the text replay method presented in Baker, Corbett & Wagner (2006). We found that feature sets based on cumulative attributes, attributes computed over all predecessor clips, yielded better detectors of CVScompliant and hypothesis-testing behavior than more local representations of student behavior. Furthermore, our detectors classify behaviors well enough to use them in our learning environment to determine which students require scaffolding on these skills.
UR - http://www.scopus.com/inward/record.url?scp=80054838991&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80054838991&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:80054838991
SN - 9780615375298
T3 - Educational Data Mining 2010 - 3rd International Conference on Educational Data Mining
SP - 181
EP - 190
BT - Educational Data Mining 2010 - 3rd International Conference on Educational Data Mining
T2 - 3rd International Conference on Educational Data Mining, EDM 2010
Y2 - 11 June 2010 through 13 June 2010
ER -