Examining consumer behaviour in the UK Energy sector through the sentimental and thematic analysis of tweets

Abstract

Consumer engagement with brands on social media has been empirically proven. However, little is known about consumers' natural behaviour on social media, as literature on this topic is still in an early stage of its evolution. Accordingly, this study aims to investigate and understand the group interactions of consumer behaviour, with a specific focus on tweets within the UK energy sector. Energy is a significant utility in the United Kingdom, and the sector is evolving more rapidly than ever before, with pressure being applied to energy suppliers to meet the demands of consumers. This study draws on social capital theory to investigate how UK consumers engage with their suppliers, as well as the knowledge‐sharing capabilities of the Twitter community. In Study 1, Python was used to conduct tweet mining and sentiment analysis to investigate the polarity in consumer engagement with 82 energy companies in the United Kingdom. Results indicated overall positive sentiments towards the energy suppliers, although the level of engagement varies across the different groups of suppliers. Study 2 followed up with a qualitative insight into the factors shaping consumers' behaviour as they engage with brands on social media. A thematic model emerges in the form of an interrelated conceptual theory comprising three stakeholders, the key relationships between them, and their natural behaviours. This study offers a contemporary, essential, and interconnected understanding of consumer behaviour online with a focus on the energy sector, and further advances research into online consumer behaviour, sentiment analysis, netnography, and social media research.

An Analysis of the #CovidPain Tweet Chat During the First Wave of the COVID-19 Pandemic in 2020

“…We acknowledge that sentiment analysis alone cannot provide an understanding of people’s experiences and what caused them to have a positive or negative attitude toward a topic or discussion [ 17 ]. Sentiment analysis is a machine learning process involving the application of natural language processing to the identification of expressions that reflect the authors’ opinion-based attitudes toward entities.…”

Post-truth, gender issues and sports entertainment: the setting in Ibero-America’s main digital media for the Super Bowl halftime show 2020

“…It is a fact that, as Joyanes-Aguilar (2013) states, data analysis has evolved as large volumes of data grew and, therefore, Big Data analytics excels as the data avalanche grows. Other reference studies such as Cloud Security Alliance (2014) with applications to various sectors and activities (Mogaji & Erkan, 2019;Mogaji, Balakrishnan & Kieu, 2020) account for the importance of linking variables and indicators arising from sophisticated AI-applying services through Big Data approaches to capturing evidence in large volumes of data and understanding the behavior of customers, users or audiences in general (Kunz et al, 2017).…”

Do Twitter sentiments really effective on energy stocks? Evidence from the intercompany dependency

“…to the identification of utterances that indicate authors' opinion-based attitudes towards items (Li et al 2017). Consistent with the previously accepted methodology for researching energy firms in the UK (Mogaji et al 2021), customer tweets were collected as a direct representation of their interactions with brands and other clients. Python was utilized for Twitter mining and sentiment analysis, notably Twitterscraper and Textblob.…”