The communication of corporate social responsibility (CSR) highlights the behavior of the business toward CSR and their framework of sustainable development (SD), thus helping policymakers understand the role businesses play with respect to the 2030 Agenda. Despite its importance, this is still a relatively underexamined and emerging topic. In our paper, we focus on what businesses communicate about CSR through social media and how this relates to the Sustainable Development Goals (SDGs). We identified the topics discussed on Twitter, their evolution over time, and the differences across sectors. We applied the structural topic model (STM) algorithm, which allowed us to estimate the model, including document-level metadata (time and sector). This model proved to be a powerful tool for topic detection and the estimation of the effects of time and sector on the discussion proportion of the topics. Indeed, we found that the topics were well identified overall, and the model allowed catching signals from the data. We derived CSR communication indexes directly from the topic model (TM) results and propose the use of dissimilarity and homogeneity indexes to describe the communication mix and highlight differences and identify clusters.
The aim of this paper is to understand why firms engage with their suppliers to collaborate for sustainability. To this purpose, we use the Carbon Disclosure Project (CDP) Supply Chain dataset and apply the Structural Topic Model to 1) identify the topics discussed in an open-ended question related to climate-related supplier engagement and 2) estimate the differences in the discussion of such topics between CDP members and non-members, respectively focal firms and first-tier suppliers. The analysis highlights that the two most prevalent reasons firms engage with their suppliers relate to several aspects of the management of the supply chain, and the services and goods mobility efficiency. It is further noted how first-tier suppliers do not dispose of established capabilities and, therefore, are still in the course of improving their processes. On the contrary, focal firms have more structured capabilities so to manage supplier engagement for information collection. This study demonstrates how big data and machine learning methods can be applied to analyse unstructured textual data from traditional surveys.
In recent years, survey data integration and inference based on non-probability samples have gained considerable attention. Because large probability-based samples can be cost-prohibitive in many instances, combining a probabilistic survey with auxiliary data is appealing to enhance inferences while reducing the survey costs. Also, as new data sources emerge, such as big data, inference and statistical data integration will face new challenges. This study aims to describe and understand the evolution of this research field over the years with an original approach based on text mining and bibliometric analysis. In order to retrieve the publications of interest (books, journal articles, proceedings, etc.), the Scopus database is considered. A collection of 1023 documents is analyzed. Through the use of such methodologies, it is possible to characterize the literature and identify contemporary research trends as well as potential directions for future investigation. We propose a research agenda along with a discussion of the research gaps which need to be addressed.
Social media are fundamental in creating new opportunities for firms and they represent a relevant tool for the communication and the engagement with customers. The purpose of this paper is to analyse the communication of Corporate Social Responsibility (CSR) activities on Twitter. We consider the listed companies included in the Dow Jones Industrial Average Index and we implement a topic model analysis on their timelines. In order to identify the topic discussed, their correlation, and their evolution over time and sectors,we apply the Structural Topic Model algorithm, which allows estimating the model including document-level metadata. This model proves to be a powerful tool for topic detection and for estimating the effects of document-level metadata. Indeed, we find that the topics are overall well identified, and the model allows catching signals from the data. Finally, we discuss issues related to the validity of the analysis, including data quality problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.