Topic Detection Based on Weak Tie Analysis： A Case Study of LIS Research

Purpose: Based on the weak tie theory, this paper proposes a series of connection indicators Acof weak tie subnets and weak tie nodes to detect research topics, recognize their connections, and understand their evolution.Design/methodology/approach: First, keywords are extracted from article titles and preprocessed. Second, high-frequency keywords are selected to generate weak tie co-occurrence networks. By removing the internal lines of clustered sub-topic networks, we focus on the analysis of weak tie subnets’ composition and functions and the weak tie nodes’ roles.Findings: The research topics’ clusters and themes changed yearly; the subnets clustered with technique-related and methodology-related topics have been the core, important subnets for years; while close subnets are highly independent, research topics are generally concentrated and most topics are application-related; the roles and functions of nodes and weak ties are diversified.Research limitations: The parameter values are somewhat inconsistent; the weak tie subnets and nodes are classified based on empirical observations, and the conclusions are not verified or compared to other methods.Practical implications: The research is valuable for detecting important research topics as well as their roles, interrelations, and evolution trends. Originality/value: To contribute to the strength of weak tie theory, the research translates weak and strong ties concepts to co-occurrence strength, and analyzes weak ties’ functions. Also, the research proposes a quantitative method to classify and measure the topics’ clusters and nodes.

Combining Topological Properties and Strong Ties for Link Prediction

Link prediction is an important task that estimates the probability of there being a link between two disconnected nodes. The similarity-based algorithm is a very popular method that employs the node similarities to find links. Most of these types of algorithms focus only on the contribution of common neighborhoods between two nodes. In sociological theory relationships within three degrees are the strong ties that can trigger social behaviors.Thus, strong ties can provide more connection opportunities for unconnected nodes in the networks. As critical topological properties in networks, nodes degrees and node clustering coefficients are well-suited for describing the tightness of connections between nodes. In this paper, we characterize node similarity by utilizing the strong ties of the ego network（i.e., paths within three degrees） and its close connections（node degrees and node clustering coefficients）. We propose a link prediction algorithm that combines topological properties with strong ties, which we called the TPSR algorithm. This algorithm includes TPSR2, TPSR3, and the TPSR4 indices. We evaluate the performance of the proposed algorithm using the metrics of precision and the Area Under the Curve（AUC）. Our experimental results show the TPSR algorithm to perform remarkably better than others.