Title: Logistic Regression-based Sentiment Classification Approach for Identifying Undergraduate Student Sentiments in a Course Studied
<br>Cover Date: 2024-01-01
<br>Cover Display Date: 2024
<br>DOI: 10.1109/RI2C64012.2024.10784409
<br>Description: This study aimed to utilize sentiment classification to ascertain the sentiment of undergraduate students towards the course they have studied. This case study specifically examines the character design course given by the Department of Creative Media, Faculty of Informatics, Mahasarakham University. Unfortunately, our data collection exhibits an imbalance between the positive class and the negative class, with a greater likelihood for the data belong to the positive class. This issue has the potential to result in sentiment classifiers that generate subpar outcomes. Consequently, this issue was also addressed in this study. To develop the binary-based sentiment classifiers, logistic regression methods were employed, specifically traditional logistic regression and logistic regression with class weights. The term weighting scheme is tf-idf, The results were determined to be satisfactory after being evaluated using the F1 score and AUC. However, it was found that the sentiment classifiers generated by L R with class weights showed better results in terms of average F1 score and AUC compared to the sentiment classifiers developed using traditional LR. The overall improvements of F1 score and AUC were 14.51 % and 13.50%, respectively.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Designing, Developing, and Efficiency Evaluation of a Smartphone Application for Blood Donation
<br>Cover Date: 2022-08-01
<br>Cover Display Date: August 2022
<br>DOI: 10.18280/isi.270406
<br>Description: This study aimed to design, develop, and evaluate efficiency of a human-based “U-Blood App” prototype for blood unavailability in Thailand. This study adopted a mixed-method design. The results of the study revealed these key findings. First, the needs analysis of 32 key informants (50% males and a mean age of 40.6 years) indicated that the features of the User Experience (UE) and the User Interface (UI) should contain blood donor’s qualification, general information record of the blood donor’s health, blood donation appointment and notification schedule, the application download and installation, a simple guide for the application user, the hospital logo, and necessary information. Second, the evaluation by experts revealed that the quality of the prototype is high (X<sup>̄</sup> =4.79) and the quality of UI (X<sup>̄</sup> =4.79) was higher than that of UE (X<sup>̄</sup> =4.70). Lastly, the end users of 65 samples (50.76% females and a mean age of 48 years) are highly satisfied with the prototype (X<sup>̄</sup> =4.68). The findings advanced the understanding of the impacts of human factors on the development of smart phone application for blood donation. The overall results cannot be generalized in the long term. Future inquiry should work on this limitation.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>