Search results

This study aims to investigate how a very particular learning environment, namely, partition rooms, affect students’ teaching experience and further explore if students’ learning styles is a pertinent determinant. Partition rooms are very common in Saudi Arabia when lectures are held by male instructors for female students. The male instructor delivers his lesson behind a glass wall, creating an environment of limited visual and auditory interaction. Various digital tools are present, meant to overcome the gap caused by the lack of direct student–teacher contact.

The researchers collected data from a sample of 109 female students who are studying at Level 4 Computer Science Department, College of Computer Sciences and Information Technology, at a public university in Saudi Arabia. All of them experienced a minimum of two courses undertaken in a partition room. The survey consists of two parts with a total of 53 questions. The first 20 questions were adopted from the perceptual learning style preference questionnaire (PLSP).

Research findings reveal that students are affected differently by the various dimensions of the partition room depending on their learning style.

There are fewer results in the literature that study learners of our particular group, namely, Saudi females. The study focuses on students studying IT and related fields. This study is almost unique, as most studies of the kind are related to the experience of females learning English as a foreign language. Therefore, the authors’ research gives much-needed insight into the conditions and perceptions of female students studying toward their degree in a technical field.

This paper aims to propose a novel way of using textual clustering as a feature selection method. It is applied to identify the most important keywords in the profile classification. The method is demonstrated through the problem of sick-leave promoters on Twitter.

Four machine learning classifiers were used on a total of 35,578 tweets posted on Twitter. The data were manually labeled into two categories: promoter and nonpromoter. Classification performance was compared when the proposed clustering feature selection approach and the standard feature selection were applied.

Radom forest achieved the highest accuracy of 95.91% higher than similar work compared. Furthermore, using clustering as a feature selection method improved the Sensitivity of the model from 73.83% to 98.79%. Sensitivity (recall) is the most important measure of classifier performance when detecting promoters’ accounts that have spam-like behavior.

The method applied is novel, more testing is needed in other datasets before generalizing its results.

The model applied can be used by Saudi authorities to report on the accounts that sell sick-leaves online.

The research is proposing a new way textual clustering can be used in feature selection.