Using Twitter to explore consumers' sentiments and their social representations towards new food trends

Abstract

PurposeThis paper investigates the use of Twitter for studying the social representations of different regions across the world towards new food trends.Design/methodology/approachA density-based clustering algorithm was applied to 7,014 tweets to identify regions of consumers sharing content about food trends. The attitude of their social representations was addressed with the sentiment analysis, and grid maps were used to explore subregional differences.FindingsTwitter users have a weak, positive attitude towards food trends, and significant differences were found across regions identified, which suggests that factors at the regional level such as cultural context determine users' attitude towards food innovations. The subregional analysis showed differences at the local level, which reinforces the evidence that context matters in consumers' attitude expressed in social media.Research limitations/implicationsThe social media content is sensitive to spatio-temporal events. Therefore, research should take into account content, location and contextual information to understand consumers' perceptions. The methodology proposed here serves to identify consumers' regions and to characterize their attitude towards specific topics. It considers not only administrative but also cognitive boundaries in order to analyse subsequent contextual influences on consumers' social representations.Practical implicationsThe approach presented allows marketers to identify regions of interest and localize consumers' attitudes towards their products using social media data, providing real-time information to contrast with their strategies in different areas and adapt them to consumers' feelings.Originality/valueThis study presents a research methodology to analyse food consumers' understanding and perceptions using not only content but also geographical information of social media data, which provides a means to extract more information than the content analysis applied in the literature.

Factors influencing user participation in social media: Evidence from twitter usage during COVID-19 pandemic in Saudi Arabia

“…The subject under study is social media users' active participation during the COVID-19 pandemic. Social media is represented here by Twitter, as this SNS plays a major role in communication during a crisis [93,94]. Twitter is fast becoming established as the prime social reporting site for disseminating information, particularly in times of crises.…”

New Trends in the Global Digital Transformation Process of the Agri-Food Sector: An Exploratory Study Based on Twitter

“…Another important aspect is the possibility to analyse sentiments to gain an understanding of the opinions from which the engagement could be addressed (Caetano et al, 2018;Veltri and Atanasova, 2015). The emotional component of tweets has been used to understand social perception towards a specific phenomenon also in the agri-food sector, such as precision agriculture (Ofori and El-Gayar, 2021), consumer opinions towards food attributes (Borrero and Zabalo, 2021;Samoggia et al, 2020) and new food trends (Pindado and Barrena, 2020). However, these studies do not go in depth in the different technologies or the user profile that are key aspects of the current study.…”

“…CA allows for mining intelligence from the captured tweets that are in the form of unstructured texts (Krippendorff, 2004). An important step in text analysis and classification, previous to the CA, is data preprocessing (e.g., cleaning, removing noise), which includes the removal of links, non-Latin characters, numbers and users (Pindado and Barrena, 2020). CA can be performed by automatic text processing methods, based on text capturing and machine learning algorithms.…”

“…For these reasons, social media data has become a popular information source for academic research and other actors. Although it has been mainly focused on the analysis of food consumer behaviour (Mishra and Singh, 2018;Mostafa, 2013;Pindado and Barrena, 2020), Twitter has been also used as an entry point for understanding perceptions of specific digital innovations in the agri-food sector by the "industry, farmers, and the broader public" (Duncan et al, 2021(Duncan et al, , p. 1185.…”

An analysis of public opinions regarding Internet-famous food: a 2016–2019 case study on Dianping

“…By mining the Twitter comments, Samoggia et al (2020) explore the views on the health attributes towards coffee with a term frequency analysis, keyword-in-context analysis and sentiment analysis. Pindado and Barrena (2020) use geographic information in social media data to analyze consumer attitudes. Calheiros et al (2017) study consumer-generated online reviews using topic modeling.…”