An intelligent student advising system using collaborative filtering

Abstract

Abstract-We propose a web based intelligent student advising system using collaborative filtering, a technique commonly used in recommendation systems assuming that users with similar characteristics and behaviors will have similar preferences. With our advising system, students are sorted into groups and given advice based on their similarities to the groups. If a student is determined to be similar to a group students, a course preferred by that group might be recommended to the student. K-means algorithm has been used to determine the similarity of the students. This is an extremely efficient and simple algorithm for clustering analysis and widely used in data mining. Given a value of K, the algorithm partitions a data set into K clusters.Seven experiments on the whole data set and ten experiments on the training data set and testing data set were conducted. A descriptive analysis was performed on the experiment results. Based on these results, K=7 was identified as the most informative and effective value for the K-means algorithm used in this system. The high performance, merit performance and low performance student groups were identified with the help of the clusters generated by the K-means algorithm. Future work will make use of a two-phase approach using Cobweb to produce a balanced tree with sub-clusters at the leaves as in [11], and then applying K-means to the resulting sub-clusters. Possible improvements for the student model were identified. Limitation of this research is discussed.

A novel integrated framework for securing online instructor-student communication

“…Results exhibited that 79% are satisfied with the proposed online advising system and 75% of the overall participants indicated that the online advising system is effective and helpful. Ganeshan and Li (2015) had also proposed a web-based intelligent student advising system in which they emphasised that students should be divided into groups. Advisors will have more time in advising students in groups that share similar interests.…”

Academic Advising Systems: A Systematic Literature Review of Empirical Evidence

“…• Authors in [5,14] suggested that students' major is a possible factor that is related to the students' performance. Experiment claim that male students aged between 24 and 27 in the software major, mostly of European, Maori, and Asian backgrounds, as well as middle aged (around 45) students, are more likely to be high performing students.…”

“…The course recommendation problem gets more complex when considering a large number of courses that have different weights, values, and priorities addressed by the Course-Petri net, a specialization of Petri net that is used on paper [26] as the foundation for development of an advising system. Student diversity is another aspect that complicates the problem [13,14]. For example, authors in [13] introduce an XML user-based collaborative system called Automatic Academic Advisor, which advises a student to take courses that were taken successfully by students with the same interests and academic performance.…”

“…For example, authors in [13] introduce an XML user-based collaborative system called Automatic Academic Advisor, which advises a student to take courses that were taken successfully by students with the same interests and academic performance. In another case study, K-means algorithm has been used to determine the similarity of the students [14].…”

“…It was identified that when K = 7, the clusters generated from the K means algorithm are more informative and effective [14] • Using an existing and relatively large dataset can be helpful in testing out the collaborative filtering signals, as well as in choosing the appropriate correlation algorithm [5] • Using friend relationships to weight the correlation used in the collaborative filtering process did not turn out to improve the accuracy of the recommendations [5] (a)…”