Beyond Influence Maximization: Volume Maximization in Social Networks

• Published in: Disease Control Through Social Network Surveillance pp. 133 - 155
• Main Authors: Choudhury, Abhinav, Kaushik, Shruti, Dutt, Varun
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Lecture Notes in Social Networks
• Subjects: Influence maximization; Influence spread; Instance-based learning; Physicians; Reinforcement learning; Social networks; Volume maximization; Volume spread
• ISBN: 3031078683; 9783031078682
• ISSN: 2190-5428; 2190-5436
• DOI: 10.1007/978-3-031-07869-9_7

The health crisis brought about by Covid-19 has resulted in a heightened necessity for proper and correct information dissemination to counter the prevalence of fake news and other misinformation. Doctors are the most reliable source of information regarding patients’ health status, disease, treatment options, or necessary lifestyle changes. Prior research has tackled the problem of influence maximization (IM), which tries to identify the most influential physicians inside a physician’s social network. However, less research has taken place on solving the problem of volume maximization (VM), which deals with finding the best set of physicians that maximize the combined volume (e.g., medicine prescribed) and influence (i.e., information disseminated). The primary objective of this work is to address the VM problem by proposing three frameworks: a reinforcement learning (RL) framework, and Instance-Based Learning (IBL), and a heuristic framework called Cost-Effective Lazy Forward (CELF)-volume algorithm, a variant of the popular CELF algorithm. We compared the proposed algorithms with a Weighted-greedy algorithm and a prefix excluding maximum influence arborescence (PMIA) IM algorithm. We used the physicianSN dataset (physician social network 181 nodes and 19,026 edges) to test different algorithms. Results revealed that the CELF-volume algorithm gave an average volume spread increment of 58% compared to the baseline algorithm but gave an average influence spread increment of only 12%. While PMIA gave the highest average influence spread increment of 46% but an average volume spread increment of only 28%. In contrast, Q-learning gave an average volume spread increment of 34% and an influence spread increment of 14%. This research highlights the utility of using reinforcement learning algorithms for finding critical physicians that can swiftly disseminate critical information to both physicians and patients.