Integrating Network Clustering Analysis and Computational Methods to Understand Communication With and About Brands: Opportunities and Challenges

Abstract

Brand-related content cocreated by consumers can play a crucial role in brand–consumer interactions and provide brands with valuable insights hidden in vast seas of unstructured data. We propose and evaluate a framework integrating a social network approach and scalable automated content analysis of texts and visuals for studying brand-related communication on social media. To illustrate the proposed approach, we use Twitter content related to two brands: Barclays and Sierra Club. By applying network clustering algorithms we identify different types of organically emerging communities around brands. Cluster-specific diffusion leaders are identified using their in-degree centrality values. To examine the unique characteristics of brand-related content within each cluster, we apply and assess the accuracy of popular off-the-shelf solutions for text and image analysis, also known as application programming interfaces (APIs). Of six sentiment analysis solutions, only one shows acceptable reliability levels. For computer vision APIs, we first identify labels that have unclear or imprecise meaning and calculate accuracy levels, resulting in acceptable accuracy levels for four of the five APIs. We discuss conceptual and practical implications of this integrative approach and of the technological hurdles that these popular automated content analysis applications pose.

Notes

1 These 1,000 tweets were coded by a student assistant. Before the coding of the full sample, a subsample of 400 tweets was also coded by the first author for intercoder reliability assessment (Krippendorff’s α = 0.624).

2 https://github.com/clips/pattern

3 https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/

4 https://cloud.google.com/natural-language

5 As Azure provided results in categories - negative, neutral, mixed, positive -, these results were used directly, with the mixed category being merged with the neutral.

6 https://cloud.google.com/vision/

7 For example, an image without people would be incorrect if labeled as “woman”; an image with a set of people discussing in a room would be correct if labeled as “education”—even if the context was not fully clear.

Additional information

Notes on contributors

Itai Himelboim

Itai Himelboim (PhD, University of Minnesota) is an associate professor of advertising and Thomas C. Dowden professor of media analytics, Grady College of Journalism and Mass Communication, University of Georgia.

Ewa Maslowska

Ewa Maslowska (PhD, University of Amsterdam) is an assistant professor, Charles H. Sandage Department of Advertising, University of Illinois at Urbana–Champaign.

Theo Araujo

Theo Araujo (PhD, University of Amsterdam) is an associate professor, Communication in the Digital Society, Amsterdam School of Communication Research, University of Amsterdam.