In this study, we present a comprehensive framework for capturing, processing, and analyzing large-scale digital communication data to uncover hidden informal communication patterns within a real-world corporate environment.
We run our study on a unique dataset of 40.425.247 email messages exchanged within a banking company, spanning a two-year period. Based on this information, we construct a social network graph highlighting the email interactions. The graph is compared with organizational data, including business unit affiliations, enabling a detailed analysis of the relationship between formal organizational structures and informal social networks. This figure shows a filtered version of the Email Interaction Graph (cleaned up and filtered data) It’s a weighted undirected graphs of email exchanges (edges) between employees (nodes). The colors represent the business units of the employees.
By applying state-of-the-art community detection algorithms, we extract informal communities and compare them to the formal structure using various external validation metrics. Our results reveal that while informal communities may overlap with the formal structure to some extent, informal communities often diverge in ways that may reveal organizational dynamics, communication flow, and inter-departmental collaboration that are not apparent from the formal structure alone. This study aims to pave the way for future research by exploring how human resource management can leverage insights derived from digital communication interactions to foster positive organizational behavior and enhance management practices.
The following diagram represents the comparison between the formal structure (on the left) and the informal structure (on the right). Lines connecting two sets represent the affiliated business unit and to which informal community an employee is associated with. The bigger the rectangles, the higher the number of employees in a partition.
The details of the study have been published and presented at the 2024 IEEE International Conference on Big Data (BigData) on 15-18 December 2024 in Washington DC in the paper:
L. Di Perna, M. Bianchi, M. Matteucci and M. Brambilla, “Unveiling Real-World Company Hidden Communication Patterns: Comparing Informal Large-Scale Email Network and Formal Structure,” 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA, 2024, pp. 3051-3060, doi: 10.1109/BigData62323.2024.10825600.
You can read the full paper here:
https://ieeexplore.ieee.org/document/10825600
Extensions, further researches and thesis opportunities are planned on this topic.
