Search for: All records

Intelligent systems to support collaborative learning rely on real-time behavioral data, including language, audio, and video. However, noisy data, such as word errors in speech recognition, audio static or background noise, and facial mistracking in video, often limit the utility of multimodal data. It is an open question of how we can build reliable multimodal models in the face of substantial data noise. In this paper, we investigate the impact of data noise on the recognition of confusion and conflict moments during collaborative programming sessions by 25 dyads of elementary school learners. We measure language errors with word error rate (WER), audio noise with speech-to-noise ratio (SNR), and video errors with frame-by-frame facial tracking accuracy. The results showed that the model’s accuracy for detecting confusion and conflict in the language modality decreased drastically from 0.84 to 0.73 when the WER exceeded 20%. Similarly, in the audio modality, the model’s accuracy decreased sharply from 0.79 to 0.61 when the SNR dropped below 5 dB. Conversely, the model’s accuracy remained relatively constant in the video modality at a comparable level (> 0.70) so long as at least one learner’s face was successfully tracked. Moreover, we trained several multimodal models and found that integrating multimodal data could effectively offset the negative effect of noise in unimodal data, ultimately leading to improved accuracy in recognizing confusion and conflict. These findings have practical implications for the future deployment of intelligent systems that support collaborative learning in actual classroom settings. 

As enrollment in CS programs have risen, it has become increasingly difficult for teaching staff to provide timely and detailed guidance on student projects. To address this, instructors use automated assessment tools to evaluate students’ code and processes as they work. Even with automation, understanding students’ progress, and more importantly, if students are making the ‘right’ progress toward the solution is challenging at scale. To help students manage their time and learn good software engineering processes, instructors may create intermediate deadlines, or milestones, to support progress. However, student’s adherence to these processes is opaque and may hinder student success and instructional support. Better understanding of how students follow process guidance in practice is needed to identify the right assignment structures to support development of high-quality process skills. We use data collected from an automated assessment tool, to calculate a set of 15 progress indicators to investigate which types of progress are being made during four stages of two projects in a CS2 course. These stages are split up by milestones to help guide student activities. We show how looking at which progress indicators are triggered significantly more or less during each stage validates whether students are adhering to the goals of each milestone. We also find students trigger some progress indicators earlier on the second project suggesting improving processes over time. 

As enrollment in CS programs have risen, it has become increasingly difficult for teaching staff to provide timely and detailed guidance on student projects. To address this, instructors use automated assessment tools to evaluate students' code and processes as they work. Even with automation, understanding students' progress, and more importantly, if students are making the 'right' progress toward the solution is challenging at scale. To help students manage their time and learn good software engineering processes, instructors may create intermediate deadlines, or milestones, to support progress. However, student's adherence to these processes is opaque and may hinder student success and instructional support. Better understanding of how students follow process guidance in practice is needed to identify the right assignment structures to support development of high-quality process skills. We use data collected from an automated assessment tool, to calculate a set of 15 progress indicators to investigate which types of progress are being made during four stages of two projects in a CS2 course. These stages are split up by milestones to help guide student activities. We show how looking at which progress indicators are triggered significantly more or less during each stage validates whether students are adhering to the goals of each milestone. We also find students trigger some progress indicators earlier on the second project suggesting improving processes over time. 

Background and Context: Researchers and practitioners have begun to incorporate collaboration in programming because of its reported instructional and professional benefits. However, younger students need guidance on how to collaborate in environments that require substantial interpersonal interaction and negotiation. Previous research indicates that feedback fosters students’ productive collaboration. Objective: This study employs an intervention to explore the role instructor-directed feedback plays on elementary students’ dyadic collaboration during 2-computer pair programming. Method: We used a multi-study design, collecting video data on students’ dyadic collaboration. Study 1 qualitatively explored dyadic collaboration by coding video transcripts of four dyads which guided the design of Study 2 that examined conversation of six dyads using MANOVA and non-parametric tests. Findings: Result from Study 2 showed that students receiving feed- back used productive conversation categories significantly higher than the control condition in the sample group considered. Results are discussed in terms of group differences in specific conversation categories. Implications: Our study highlights ways to support students in pair programming contexts so that they can maximize the benefits afforded through these experiences. 

Students’ interactions with online tools can provide us with insights into their study and work habits. Prior research has shown that these habits, even as simple as the number of actions or the time spent on online platforms can distinguish between the higher performing students and low-performers. These habits are also often used to predict students’ performance in classes. One key feature of these actions that is often overlooked is how and when the students transition between different online platforms. In this work, we study sequences of student transitions between online tools in blended courses and identify which habits make the most difference between the higher and lower performing groups. While our results showed that most of the time students focus on a single tool, we were able to find patterns in their transitions to differentiate high and low performing groups. These findings can help instructors to provide procedural guidance to the students, as well as to identify harmful habits and make timely interventions.