Abstract
To scientifically and accurately recommend suitable teachers for university courses and improve teaching quality, designing an effective recommendation algorithm is necessary. Therefore, we construct quantitative models of teacher characteristics, course characteristics, and teaching evaluations under the theories and methods of education and build a sparse experimental data matrix based on the quantified data. On this basis, we propose a teacher recommendation algorithm (PRLFM) based on the improved latent factor model (LFM) and the improved PersonalRank algorithm. Firstly, the improved LFM is used to predict the evaluation scores of those courses that teachers have not taught. The scores which are higher than the specified threshold are used to fill the corresponding missing items in the sparse matrix to reduce the matrix's sparsity. Then, the bipartite graph model based on the teacher set and course set is constructed according to the filled experimental data matrix. The weight of edges in the bipartite graph is replaced by the teacher and course's evaluation score multiplied by the course difficulty, which reflects the correlation between course and evaluation score. Next, an improved probability transition matrix based on the bipartite graph is constructed. The access probability in the matrix is replaced by the node's out degree's reciprocal multiplied by the edge's weight. The correlation degree between the course and all teachers is quickly calculated using the matrix algorithm of PersonalRank. Finally, a teacher recommendation model is constructed to realize teachers' top-N recommendation by combining the correlation degree with teachers' characteristics. Experiments show that the PRLFM algorithm can effectively improve the accuracy of prediction and top-N recommendation. It solves the problem of lack of scientific basis in recommending suitable teachers for university courses and improving the teaching quality.
Highlights
Universities are developing in the continuous reform, in which the continuous introduction to professional teachers and the continuous updating of courses are the main content of development
The rest of the study was constructed as follows: In Section 2, we described the detailed algorithm of latent factor model (LFM) and PersonalRank
The average prediction accuracy of User-collaborative filtering (CF) is lower than PRLFM and LFM 13.97% and 9.22%, Item-CF is lower than PRLFM and LFM 16.72% and 12.18%, LFM is lower than PRLFM 5.57%
Summary
Universities are developing in the continuous reform, in which the continuous introduction to professional teachers and the continuous updating of courses are the main content of development. To solve the above problems, we designed a hybrid algorithm (PRLFM) of teacher recommendation based on the improved LFM and PersonalRank by adopting a cascade hybrid method [56] with feature extension [57]. Because the improved LFM can reasonably decompose the highdimensional dataset into the dot product of two low dimensional matrices, reflect the implicit relationship between the data, and reasonably predict the evaluation score larger than the specified threshold the course not taught by the teacher. A weighted bipartite graph model of teachers and courses was established according to the experimental dataset matrix predicted by the improved LFM. Assuming that there are n users and items, let M be the norder transition probability matrix of a binary graph, namely: At this point, the iterative equation of the random walk idea is expressed as:. It only needs to calculate (1-αMT) once, but it needs to rapidly calculate the sparse matrix’s inverse matrix
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
