Key Student Nodes Mining in the In-Class Social Network Based on Combined Weighted GRA-TOPSIS Method

Abstract

In this paper, a key node mining algorithm of entropy-CRITIC combined weighted GRA-TOPSIS method is proposed, which is based on the network structure features. First, the method obtained multi-dimensional data of students' identities, seating relationships, social relationships, and so on to build a database. Then, the seating similarity among students was used to construct the in-class social networks and analyze the structural characteristics of them. Finally, the CRITIC and entropy weight method was introduced for obtaining the combined weight values and the GRA-TOPSIS multi-decision fusion algorithm to mine the key student nodes that have negative impact. The experiments showed that the algorithm of this paper can evaluate students objectively based on their classroom social networks, providing technical support for process-oriented comprehensive quality education evaluation.

Research on Knowledge Tracing-Based Classroom Network Characteristic Learning Engagement and Temporal-Spatial Feature Fusion

“…Therefore, in a smart classroom, the students' heads-up learning states are monitored through the video surveillance system, and through correlation analysis with learning engagement, teachers can better observe and assess students' learning states. Based on the analytical model proposed by Shou et al [30] for assessing learners' head posture in smart classroom videos, the head-up rate of learner u i during the duration of learning k knowledge points is obtained by…”

The NEDC-GTOPSIS Node Influence Evaluation Algorithm Based on Multi-Layer Heterogeneous Classroom Networks

“…Yang et al (2018) proposed a dynamic TOPSIS method based on the GRA algorithm and SIR model to identify key nodes. In the research on classroom social networks, Shou et al (2023) utilized students' seat similarity to construct a classroom social network. They then employed the GRA-TOPSIS algorithm to unearth key student nodes with negative impact.…”

“…In Figure 2(b), which illustrates the G IR network, the size of each node is proportional to its degree (i.e., the number of adjacent nodes connected to it). Seat allocation using linear regression model (Shou et al, 2023)Face detection using MTCNN (Zhang et al, 2020)Face recognition using FaceNet (Schroff et al, 2015) StudentInteractionData -Interaction relationships Analyzed and recorded from classroom videosAn interaction is considered to occur when the interaction time exceeds τ seconds…”

“…The experiment compares the information transmission rate r(t) of influential nodes extracted using the NEDC-GTOPSIS algorithm proposed in this article against those obtained through algorithms like PageRank, Eigenvector Centrality, Closeness Centrality, Degree Centrality, and GRA-TOPSIS (Shou et al, 2023). As shown in Figure 8, the r(t) curves reveal that the influential nodes identified by the algorithm reach steady-state conditions more rapidly in G FR , G CR , and G SS networks, with the steady-state r(t) values aligning closely with those of other algorithms.…”

“…To further demonstrate the accuracy of the NEDC-GTOPSIS algorithm in mining influential nodes in MLH classroom networks, experiments were conducted based on the combined G MLH network (G MLH = G CR + G SS ) and on the seating relationship network G SS or the composite relationship network G CR . The influential node mining results obtained using the GRA-TOPSIS algorithm (Shou et al, 2023) were compared with those obtained using the NEDC-GTOPSIS algorithm. The comparative results are presented in Table 7, showing the top six influential nodes mined by both algorithms across the three networks.…”