Capturing Student Feedback and Emotions in Large Computing Courses: A Sentiment Analysis Approach

Neumann, Marion; Linzmayer, Robin

doi:10.1145/3408877.3432403

Cited by 8 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of large computer science classes, dictionary-based SA revealed that students' grades and their emotional experiences were not correlated thus emphasizing the need to monitor student emotions in addition to assignment or exam performance when managing high-enrollment courses (Neumann and Linzmayer 2021).…”

Section: Understanding Student Populationsmentioning

confidence: 99%

“…Additionally, the SR label distribution shown in Figure 2 is extremely left-skewed with a relatively high number of neutral labels, whereas both the distribution of HE, CS, and CS+SR labels is closer to a bi-modal distribution. Neutral labels are considered an easy way out for students to not take sides (Neumann and Linzmayer 2021). Furthermore, the SR labels often disagree with the written text.…”

Section: Answering Rq1mentioning

confidence: 99%

“…Periodically collecting student feedback in the form of free-form text or Likert-style survey questions is one approach to bridge this feedback gap. Assessing this feedback in a timely manner allows instructors to learn about course materials students struggle with, gain awareness of teams that have issues, or even identify students that fall behind (Ahadi et al 2015;Presler-Marshall, Heckman, and Stolee 2022;Gitinabard et al 2022;Neumann and Linzmayer 2021). Likert-type survey questions are easy to analyze but need to be carefully tailored to specific contexts and the responses tend to be unreliable (Holzbach 1978;Leising et al 2016;Murphy 1993).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Practical Sentiment Analysis for Education: The Power of Student Crowdsourcing

Kasumba,

Neumman

2024

AAAI

View full text Add to dashboard Cite

Sentiment analysis provides a promising tool to automatically assess the emotions voiced in written student feedback such as periodically collected unit-of-study reflections. The commonly used dictionary-based approaches are limited to major languages and fail to capture contextual differences. Pretrained large language models have been shown to be biased and online versions raise privacy concerns. Hence, we resort to traditional supervised machine learning (ML) approaches which are designed to overcome these issues by learning from domain-specific labeled data. However, these labels are hard to come by -- in our case manually annotating student feedback is prone to bias and time-consuming, especially in high-enrollment courses. In this work, we investigate the use of student crowdsourced labels for supervised sentiment analysis for education. Specifically, we compare crowdsourced and student self-reported labels with human expert annotations and use them in various ML approaches to evaluate the performance on predicting emotions of written student feedback collected from large computer science classes. We find that the random forest model trained with student-crowdsourced labels tremendously improves the identification of reflections with negative sentiment. In addition to our quantitative study, we describe our crowdsourcing experiment which was intentionally designed to be an educational activity in an introduction to data science course.

show abstract

Section: Understanding Student Populationsmentioning

confidence: 99%

Section: Answering Rq1mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Practical Sentiment Analysis for Education: The Power of Student Crowdsourcing

Kasumba,

Neumman

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Many DEERS participants have gone on to publish on their research studies developed for the workshop [5,6,9,13,15,[29][30][31]38]. In several cases, their participation in DEERS lead to additional CER work beyond their original study including successful grant proposals.…”

Section: Alumni Recognitionmentioning

confidence: 99%

Training Computing Educators to Become Computing Education Researchers

Carver

Heckman

Sherriff

2022

Proceedings of the 53rd ACM Technical Symposium on Computer Science Education

View full text Add to dashboard Cite

The computing education community endeavors to consistently move forward, improving the educational experience of our students. As new innovations in computing education practice are learned and shared, however, these papers may not exhibit the desired qualities that move simple experience reports to true Scholarship of Teaching and Learning (SoTL). We report on our six years of experience in running professional development for computing educators in empirical research methods for social and behavioral studies in the classroom. Our goal is to have a direct impact on instructors who are in the beginning stages of transitioning their educational innovations from anecdotal to empirical results that can be replicated by instructors at other institutions. To achieve this, we created a year-long mentoring experience, beginning with a multi-day workshop on empirical research methods during the summer, followed by regular mentoring sessions with participants, and culminating in a follow-up session at the following year's SIGCSE Technical Symposium. From survey results and as evidenced by eventual research results and publications from participants, we believe that our method of structuring empirical research professional development was successful and could be a model for similar programs in other areas.

show abstract

“…This innovative addition seeks to mitigate potential distortions in sentiment interpretation, ensuring a more accurate portrayal of user sentiments [17]- [19]. Preliminary studies incorporating negation handling demonstrate promising outcomes [20]- [23], showcasing a notable 5-7 p.p improvement in test results [4], [18].…”

mentioning

confidence: 99%

Improving sentiment analysis on PeduliLindungi comments: a comparative study with CNN-Word2Vec and integrated negation handling

Jayadianti,

Arianti,

Cahyana

et al. 2023

SITech

View full text Add to dashboard Cite

This study investigates sentiment analysis in Google Play reviews of the PeduliLindungi application, focusing on the integration of negation handling into text preprocessing and comparing the effectiveness of two prominent methods: CNN-Word2Vec CBOW and CNN-Word2Vec SkipGram. Through a meticulous methodology, negation handling is incorporated into the preprocessing phase to enhance sentiment analysis. The results demonstrate a noteworthy improvement in accuracy for both methods with the inclusion of negation handling, with CNN-Word2Vec SkipGram emerging as the superior performer, achieving an impressive 76.2% accuracy rate. Leveraging a dataset comprising 13,567 comments, this research introduces a novel approach by emphasizing the significance of negation handling in sentiment analysis. The study not only contributes valuable insights into the optimization of sentiment analysis processes but also provides practical considerations for refining methodologies, particularly in the context of mobile application reviews.

show abstract

Capturing Student Feedback and Emotions in Large Computing Courses: A Sentiment Analysis Approach

Cited by 8 publications

References 23 publications

Practical Sentiment Analysis for Education: The Power of Student Crowdsourcing

Practical Sentiment Analysis for Education: The Power of Student Crowdsourcing

Training Computing Educators to Become Computing Education Researchers

Improving sentiment analysis on PeduliLindungi comments: a comparative study with CNN-Word2Vec and integrated negation handling

Contact Info

Product

Resources

About