Assessing the Collaboration Quality in the Pair Program Tracing and Debugging Eye-Tracking Experiment

Villamor, Maureen; Paredes, Yancy Vance; Samaco, Japheth Duane; Cortez, Joanna Feliz; Martínez, Julián; Rodrigo, Ma. Mercedes T.

doi:10.1007/978-3-319-61425-0_67

Cited by 9 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In one of the exploratory analysis conducted using half of the dataset in this study, it was found that low proficiency pairs have significantly higher RR, DET, ENTR, and LAM than highly proficient and mixed proficiency pairs (Villamor and Rodrigo 2017a). To extend this previous finding, ANOVA was performed on the CRQA results based on the pairs' proficiency levels.…”

Section: Controlling For Confoundsmentioning

confidence: 69%

“…Our previous studies on the use of CRQA characterized collaboration patterns according to participants' prior knowledge (Villamor and Rodrigo 2017a), degree of acquaintanceship (Villamor and Rodrigo 2018a), both prior knowledge and degree of acquaintanceship (Villamor and Rodrigo 2017c), and determining leader-follower profiles Villamor and Rodrigo (2017b). Cross-recurrence was also found to be positively correlated to team performance (Cherubini et al 2010;Zheng et al 2016).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gaze collaboration patterns of successful and unsuccessful programming pairs using cross-recurrence quantification analysis

Villamor

Rodrigo

2019

RPTEL

View full text Add to dashboard Cite

A dual eye tracking experiment was performed on pairs of novice programmers as they traced and debugged fragments of code. These programming pairs were categorized into successful and unsuccessful pairs based on their debugging scores. Cross-recurrence quantification analysis (CRQA), an analysis using cross-recurrence plots (CRP), was used to determine whether there are significant differences in the gaze collaboration patterns between these pair categories. Results showed that successful and unsuccessful pairs can be characterized distinctively based on their CRPs and CRQA metrics. This study also attempted to interpret the CRQA metrics in relation to how the pairs collaborated in order to provide a somewhat clear picture of their relevance and meaning. The analysis results could serve as a precursor in helping us understand what makes a programming pair more successful over other pairs and what behaviors exhibited by unsuccessful pairs that should be avoided.

show abstract

Section: Controlling For Confoundsmentioning

confidence: 69%

Section: Introductionmentioning

confidence: 99%

Gaze collaboration patterns of successful and unsuccessful programming pairs using cross-recurrence quantification analysis

Villamor

Rodrigo

2019

RPTEL

View full text Add to dashboard Cite

show abstract

“…In recent decades, educational datasets have become increasingly rich and complex, offering many opportunities for analysing student behaviour to improve educational outcomes. The analysis of student behaviour, particularly temporal trends in this behaviour, has played a major role in many recent studies in areas including automated feedback provision [8,12,16,19], dropout analysis [17,18,22], collaborative learning [4,21,23] and student equity [6,9,13].…”

Section: Introductionmentioning

confidence: 99%

DETECT: A Hierarchical Clustering Algorithm for Behavioural Trends in Temporal Educational Data

McBroom

Yacef

Koprinska

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Techniques for clustering student behaviour offer many opportunities to improve educational outcomes by providing insight into student learning. However, one important aspect of student behaviour, namely its evolution over time, can often be challenging to identify using existing methods. This is because the objective functions used by these methods do not explicitly aim to find cluster trends in time, so these trends may not be clearly represented in the results. This paper presents 'DETECT' (Detection of E ducational T rends E licited by C lustering T ime-series data), a novel divisive hierarchical clustering algorithm that incorporates temporal information into its objective function to prioritise the detection of behavioural trends. The resulting clusters are similar in structure to a decision tree, with a hierarchy of clusters defined by decision rules on features. DETECT is easy to apply, highly customisable, applicable to a wide range of educational datasets and yields easily interpretable results. Through a case study of two online programming courses (N > 600), this paper demonstrates two example applications of DETECT: 1) to identify how cohort behaviour develops over time and 2) to identify student behaviours that characterise exercises where many students give up.

show abstract

Section: Introductionmentioning

confidence: 99%

DETECT: A Hierarchical Clustering Algorithm for Behavioural Trends in Temporal Educational Data

McBroom,

Yacef,

Koprinska

2020

Preprint

View full text Add to dashboard Cite

Techniques for clustering student behaviour offer many opportunities to improve educational outcomes by providing insight into student learning. However, one important aspect of student behaviour, namely its evolution over time, can often be challenging to identify using existing methods. This is because the objective functions used by these methods do not explicitly aim to find cluster trends in time, so these trends may not be clearly represented in the results. This paper presents 'DETECT' (Detection of Educational Trends Elicited by Clustering Time-series data), a novel divisive hierarchical clustering algorithm that incorporates temporal information into its objective function to prioritise the detection of behavioural trends. The resulting clusters are similar in structure to a decision tree, with a hierarchy of clusters defined by decision rules on features. DETECT is easy to apply, highly customisable, applicable to a wide range of educational datasets and yields easily interpretable results. Through a case study of two online programming courses (N > 600), this paper demonstrates two example applications of DETECT: 1) to identify how cohort behaviour develops over time and 2) to identify student behaviours that characterise exercises where many students give up.

show abstract

Assessing the Collaboration Quality in the Pair Program Tracing and Debugging Eye-Tracking Experiment

Cited by 9 publications

References 3 publications

Gaze collaboration patterns of successful and unsuccessful programming pairs using cross-recurrence quantification analysis

Gaze collaboration patterns of successful and unsuccessful programming pairs using cross-recurrence quantification analysis

DETECT: A Hierarchical Clustering Algorithm for Behavioural Trends in Temporal Educational Data

DETECT: A Hierarchical Clustering Algorithm for Behavioural Trends in Temporal Educational Data

Contact Info

Product

Resources

About