A Knowledge-Fusion Ranking System with an Attention Network for Making Assignment Recommendations

Abstract

In recent decades, more teachers are using question generators to provide students with online homework. Learning-to-rank (LTR) methods can partially rank questions to address the needs of individual students and reduce their study burden. Unfortunately, ranking questions for students is not trivial because of three main challenges: (1) discovering students’ latent knowledge and cognitive level is difficult, (2) the content of quizzes can be totally different but the knowledge points of these quizzes may be inherently related, and (3) ranking models based on supervised, semisupervised, or reinforcement learning focus on the current assignment without considering past performance. In this work, we propose KFRank, a knowledge-fusion ranking model based on reinforcement learning, which considers both a student’s assignment history and the relevance of quizzes with their knowledge points. First, we load students’ assignment history, reorganize it using knowledge points, and calculate the effective features for ranking in terms of the relation between a student’s knowledge cognitive and the question. Then, a similarity estimator is built to choose historical questions, and an attention neural network is used to calculate the attention value and update the current study state with knowledge fusion. Finally, a rank algorithm based on a Markov decision process is used to optimize the parameters. Extensive experiments were conducted on a real-life dataset spanning a year and we compared our model with the state-of-the-art ranking models (e.g., ListNET and LambdaMART) and reinforcement-learning methods (such as MDPRank). Based on top- k nDCG values, our model outperforms other methods for groups of average and weak students, whose study abilities are relatively poor and thus their behaviors are more difficult to predict.

Digital Management and Optimization of Tourism Information Resources Based on Machine Learning

“…Because of the variability of retrieval information options, documents with high relevance are more important than documents with low relevance, so an evaluation index is put forward. Because of the maintenance of these scores, the loss function cannot be increased, and the loss function is optimized with a large slope [17].…”

Discovering Knowledge-Point Importance From the Learning-Evaluation Data

“…projected student and learning-evaluation data onto the factor vector, modeled their interaction using multiple neural layers, and proposed a neural network cognitive diagnosis model. Using the correlation between knowledge-points in the learning-evaluation data, Jin et al (2020) updated student learning statuses, to rank the questions and recommend them to the students. According to the learning-evaluation data of students, Chen and Sue (2013) used an association rule algorithm to automatically generate concept maps without expert intervention, that is, to calculate the frequency of correctly answered questions between two knowledge points.…”