Jointly Modeling Individual Student Behaviors and Social Influence for Prediction Tasks

Abstract

Prediction tasks about students such as predicting students' academic performances have practical real-world significance at both the student level and the college level. With the rapid construction of smart campuses, colleges not only offer residence and academic programs but also record students' daily life. The digital footprints provide an opportunity to offer better solutions for prediction tasks. In this paper, we aim to propose a general deep neural network which can jointly model student heterogeneous daily behaviors generated from digital footprints and social influence to deal with prediction tasks. To this end, we design a variant of LSTM and a novel attention mechanism to model the daily behavior sequence. The proposed LSTM is able to consider context information (e.g., weather conditions) while modeling the daily behavior sequence. The proposed attention mechanism can dynamically learn the different importance degrees of different days for every student. Based on behavior information, we propose an unsupervised way to construct a social network to model social influence. Moreover, we design a residual network based decoder to model the complex interactions between the features and get the predicted values such as future academic performances. Qualitative and quantitative experiments on two real-world datasets collected from a college have demonstrated the effectiveness of our model.

Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

“…where F(•) is the residual function (i.e., two combinations of "FC+PReLU+Dropout") and λ is the block index. The dimensions of X (λ−1) and F(X (λ−1) ) must be equal in Equation (18). If the dimensions are not equal, we can perform a linear transformation by the skip connection:…”

“…• JMBS [18]: JMBS is proposed in our preliminary work. It leverages multiple context-aware LSTMs and an attention mechanism to model daily behavior sequences.…”

“…We investigate the influence of the activation functions on the proposed model. We replace PReLU with ReLU or tanh in Equation ( 16), (18), and (19). Figure 13 shows the results.…”

“…To address the above challenges, we first propose a general neural network called JMBS in our preliminary work [18]. More specifically, each kind of daily behavior sequence is modeled by a variant of LSTM.…”

Infrastructure Elements for Smart Campuses: A Bibliometric Analysis

“…Modularity 6-Internet of things (IoTs) and smart buildings (Sources:[29,54,77,[94][95][96][97][98][99][100][101][102][103]). Modularity 8-Performance measurement and forecasting (Sources:[12,35,43,58,99,[110][111][112][113][114]). Modularity 9-Smart campus applications (Sources:[2,90,99,[115][116][117][118][119]).…”