How Does Students’ Help-Seeking Behaviour Affect Learning?

Mathews, Moffat; Mitrovic, Tanja

doi:10.1007/978-3-540-69132-7_40

Cited by 8 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been previously found that students who consistently use high-level help in SQL-Tutor frequently employ a "guess then copy" strategy [17]. It is worth noting that both of these strategies could be followed by self-explaining after reading the answer (cf.…”

Section: Learning Environment and Gaming Behaviorsmentioning

confidence: 99%

“…Other common gaming behaviors include intentional entering the same answer or a blank answer. In previous analyses within SQL-Tutor, these attempts, labeled as requests for help, have been manually distinguished from valid forms of help-seeking [17]. Intentional rapid mistakes have also been seen in the Andes learning environment [21].…”

Section: Learning Environment and Gaming Behaviorsmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Gaming the System in Constraint-Based Tutors

Baker

Mitrović

Mathews

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract.Recently, detectors of gaming the system have been developed for several intelligent tutoring systems where the problem-solving process is reified, and gaming consists of systematic guessing and help abuse. Constraint-based tutors differ from the tutors where gaming detectors have previously been developed on several dimensions: in particular, higher-level answers are assessed according to a larger number of finer-grained constraints, and feedback is split into levels rather than an entire help sequence being available at any time. Correspondingly, help abuse behaviors differ, including behaviors such as rapidly repeating the same answer or blank answers to elicit complete answers from the system. We use text replay labeling in combination with educational data mining methods to create a gaming detector for SQL-Tutor, a popular constraint-based tutor. This detector assesses gaming at the level of multiplesubmission sequences and is accurate both at identifying gaming within submission sequences and at identifying how much each student games the system. It achieves only limited success, however, at distinguishing different types of gaming behavior from each other.

show abstract

Section: Learning Environment and Gaming Behaviorsmentioning

confidence: 99%

Section: Learning Environment and Gaming Behaviorsmentioning

confidence: 99%

Detecting Gaming the System in Constraint-Based Tutors

Baker

Mitrović

Mathews

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, as Figure 2 shows, the hint takers tend to spend less time on a question than the learners who attempt the question, irrespective of whether the question is correctly or incorrectly answered. The research on this subject shows that the learners who attempt a question tend to have a higher probability of achieving proficiency in the subject [19]. Also, the learners who use hints very frequently tend to have the lowest learning rate [13].…”

Section: Introduction * These Authors Contributed Equallymentioning

confidence: 99%

“…We show that explicitly modeling the hint-taking behavior improves performance of the model. Additionally, a higher propensity to take hints might be informative about the likelihood of answering questions correctly [19,13]. Hence, throwing away the data points where hints were taken is akin to throwing away useful information.…”

Section: Introduction * These Authors Contributed Equallymentioning

confidence: 99%

See 1 more Smart Citation

Modeling Hint-Taking Behavior and Knowledge State of Students with Multi-Task Learning

Chaudhry¹,

Singh²,

Dogga³

et al. 2018

EasyChair Preprints

View full text Add to dashboard Cite

Interactive learning environments facilitate learning by providing hints to fill the gaps in the understanding of a concept. Studies suggest that hints are not used optimally by learners. Either they are used unnecessarily or not used at all. It has been shown that learning outcomes can be improved by providing hints when needed. An effective hinttaking prediction model can be used by a learning environment to make adaptive decisions on whether to withhold or provide hints. Past work on student behavior modeling has focused extensively on the task of modeling a learner's state of knowledge over time, referred to as knowledge tracing. The other aspects of a learner's behavior such as tendency to use hints has garnered limited attention. Past knowledge tracing models either ignore the questions where a hint was taken or label hints taken as an incorrect response. We propose a multi-task memory-augmented deep learning model to jointly predict the hint-taking and the knowledge tracing task. The model incorporates the effect of past responses as well as hints taken on both the tasks. We apply the model on two datasets -ASSISTments 2009-10 skill builder dataset and Junyi Academy Math Practicing Log. The results show that deep learning models efficiently leverage the sequential information present in a learner's responses. The proposed model significantly out-performs the past work on hint prediction by at least 12% points. Moreover, we demonstrate that jointly modeling the two tasks improves performance consistently across the tasks and the datasets, albeit by a small amount.

show abstract