Search results

As human beings step into the age of information network, big data technology is constantly improving the intelligence level of various agents such as individuals and enterprises. The crowd decision-making of the intellectual community plays an important role in the active participation of many individuals and schools in giving their wisdom, effectively solve the problems of negative internet communication, single publicity media and unprofessional promotion team in WeChat public account.

This paper aims to optimize the content and improve the effectiveness of network ideological and political education in universities. This study analyzes five highly popular WeChat public accounts at the Central University of Finance and Economics in 2019. It obtains the popularity index of tweets using the WeChat communication index algorithm and finds that the important factors that influence tweet popularity are release time and content value.

To improve the public account tweets, this study highlights the connection between the tweets’ value and students’ emotional needs, which enhances the value of tweet content in students’ life and provides more original and distinctive content.

This study found that the content and interest of college students are tweet time, tweet value and tweet content. Therefore, the public account of college ideological and political education should be improved from the following three aspects: realizing the connection between the value of tweet content and students’ emotional needs; enhancing the value of tweet content in students’ life and learning; and insisting on the original and distinctive original intention of tweet content.

Misinformation is notoriously difficult to combat. Although social media firms have focused on combating the publication of misinformation, misinformation accusations, an important by-product of the spread of misinformation, have been neglected. The authors offer insights into factors contributing to the spread of misinformation accusations on social media platforms.

The authors use a corpus of 234,556 tweets about the 2020 US presidential election (Study 1) and 99,032 tweets about the 2022 US midterm elections (Study 2) to show how the sharing of misinformation accusations is explained by locomotion orientation.

The study findings indicate that the sharing of misinformation accusations is explained by writers' lower locomotion orientation, which is amplified among liberal tweet writers.

Practitioners and policymakers can use the study findings to track and reduce the spread of misinformation accusations by developing algorithms to analyze the language of posts. A limitation of this research is that it focuses on political misinformation accusations. Future research in different contexts, such as vaccines, would be pertinent.

The authors show how social media firms can identify messages containing misinformation accusations with the potential to become viral by considering the tweet writer's locomotion language and geographical data.

Early identification of messages containing misinformation accusations can help to improve the quality of the political conversation and electoral decision-making.

Strategies used by social media platforms to identify misinformation lack scale and perform poorly, making it important for social media platforms to manage misinformation accusations in an effort to retain trust. The authors identify linguistic and geographical factors that drive misinformation accusation retweets.

As public health professionals strive to promote vaccines for inoculation efforts, fervent anti-vaccination movements are marshaling against it. This study is motived by a need to better understand the online discussion around vaccination. The authors identified the sentiments, emotions and topics of pro- and anti-vaxxers’ tweets, investigated their change since the pandemic started and further examined the associations between these content features and audiences’ engagement.

Utilizing a snowball sampling method, data were collected from the Twitter accounts of 100 pro-vaxxers (266,680 tweets) and 100 anti-vaxxers (248,425 tweets). The authors are adopting a zero-shot machine learning algorithm with a pre-trained transformer-based model for sentiment analysis and structural topic modeling to extract the topics. And the authors use the hurdle negative binomial model to test the relationships among sentiment/emotion, topics and engagement.

In general, pro-vaxxers used more positive tones and more emotions of joy in their tweets, while anti-vaxxers utilized more negative terms. The cues of sadness predominantly encourage retweets across the pro- and anti-vaccine corpus, while tweets amplifying the emotion of surprise are more attention-grabbing and getting more likes. Topic modeling of tweets yields the top 15 topics for pro- and anti-vaxxers separately. Among the pro-vaxxers’ tweets, the topics of “Child protection” and “COVID-19 situation” are positively predicting audiences’ engagement. For anti-vaxxers, the topics of “Supporting Trump,” “Injured children,” “COVID-19 situation,” “Media propaganda” and “Community building” are more appealing to audiences.

This study utilizes social media data and a state-of-art machine learning algorithm to generate insights into the development of emotionally appealing content and effective vaccine promotion strategies while combating coronavirus disease 2019 and moving toward a global recovery.

The peer review history for this article is available at https://publons.com/publon/10.1108/OIR-03-2022-0186

This study aims to investigate how New Zealand companies use Twitter to communicate and engage effectively with stakeholders during the COVID-19 pandemic.

This study proposes a conceptual framework for effective stakeholder engagement by using social media to analyse the themes and emotion of company tweets during the COVID-19 pandemic in New Zealand. The engagement of stakeholders with these tweets is also examined. This study argues that companies use selected themes and emotive language to connect with their stakeholders.

The findings show that selective themes and emotions are useful in company COVID-19 tweets to engage with the stakeholders. COVID-19 tweets contained significantly more emotion than non-COVID tweets, with emotions that can convey empathy being the most common. By presenting themselves as real, personable and empathetic towards others through emotive language, companies can engage in more meaningful and ethical way with their stakeholders.

The paper has implications for managing company communications by providing empirical evidence that both the themes and emotion expressed in the messages are important for effective stakeholder engagement in social media.

The conceptual framework for effective stakeholder engagement using social media is novel and can be used to evaluate and investigate stakeholder engagement during a global crisis.

This paper examines user generated social media content bearing on consumers’ attitude and belief systems taking the domain of natural food product as illustrative case. This research sheds light on how consumers think and talk about natural food within the context of food well-being and health.

The authors used a keyword-based approach to extract user generated content from Twitter and used both food as well-being and food as health frameworks for analysis of more than two million tweets.

The authors found that consumers mostly discuss food marketing and less frequently discuss food policy. Their results show that tweets regarding naturalness were significantly less frequent in food categories that feature naturalness to an extent, e.g. fruits and vegetables, compared to food categories dominated by technologies, processing and man-made innovation, such as proteins, seasonings and snacks.

This paper provides numerous implications and contributions to the literature on consumer behavior, marketing and public policy in the domain of natural food.

The authors’ exploratory findings can be used to guide food system stakeholders, farmers and food processors to obtain insights into consumers' mindset on food products, novel concepts, systems and diets through social media analytics.

The authors’ results contribute to the literature on the use of social media in food marketing on understanding consumers' attitudes and beliefs toward natural food, food as the well-being literature and food as the health literature, by examining the way consumers think about natural (versus man-made) food using user generated content of Twitter, which has not been previously used.

The article examines how the two Cypriot leaders – the Greek-Cypriot community leader Nicos Anastasiades and the Turkish-Cypriot community leader Mustafa Akinci – have used their Twitter accounts during the period leading to the intensification of the Cyprus peace process between 30 April 2015 and 31 October 2016.

This article presents, using descriptive analysis and thematic analysis, how the two leaders have used Twitter in the negotiations' period.

The analysis shows that the leaders, during the time frame examined, developed both pro-peace discourses around the Cyprus problem and para-social and vicarious intergroup contact that contributed in what Hogg (2015) defines an intergroup relational identity that is an effective form of “bridging” leadership across communities.

The article argues that Twitter is a tool that, in the hands of political leaders in segregated public spheres caused by yet unresolved ethnic conflicts, can become a useful tool for constructing both a positive meaning around issues concerning the rival sides and transforming opposing social identities in the formation of an “extended sense of self that includes the collaboration partner” (Hogg, 2015, p. 191).

The peer-review history for this article is available at: https://publons.com/publon/10.1108/OIR-03-2022-0161

Anthropomorphized brands have been widely used as marketing communication tools to engage consumers on social media, especially on Twitter. Guided by the social exchange theory (SET) and the dialogic theory, this study aims to investigate how anthropomorphized brands leverage different communication strategies on Twitter and how these strategies are related to consumer engagement.

Supervised machine learning was used to identify the communication strategies (i.e. message types and dialogic principles) of 125,887 tweets from 21 brand characters. Some statistical analyses (e.g. frequency analysis, Chi-square analysis and Poisson regression analysis) were performed to explore the relationships between communication strategies and consumer engagement (i.e. retweets and replies).

The majority of anthropomorphized brands’ tweets belonged to the socioemotional category and the most adopted dialogic principles were generation of return visits and conservation of visitors. Consumers engaged more with socioemotional tweets as well as the tweets that adopted the principles of dialogic loop and conservation of visitors. There were clear relationships between message types and dialogic principles in anthropomorphized brands’ tweets, and certain dialogic principles were found to effectively improve consumer engagement with certain message types.

To the best of the authors’ knowledge, this study is the first to investigate the communication strategies of anthropomorphized brand characters on Twitter using computational research methods. It not only provides brand managers a systematic review of how current anthropomorphized brands communicate with consumers on Twitter and what strategies work more effectively to trigger consumer engagement but also contributes to theory building in brand management by integrating the SET and the dialogic theory in brand anthropomorphism research.

The purpose of this paper is to analyze the correlation between the Twitter activity of two airline companies and their stock performance at the Istanbul Stock Exchange (BIST).

Overall, 113,018 tweets were divided into 34,152 semantic and 78,866 share tweets. Semantic tweets are tweets mentioning company’s products or services and were labeled manually and with deep learning models. Share tweets were divided into 13,618 relevant and 65,248 irrelevant tweets.

A positive correlation was found between share tweets and stock performance. Semantic tweets did not display a correlation with stock performance. Relevant share tweets displayed as a strong correlation as all share tweets for one company. Also, the manual labeling of 8,000 tweets led to the discovery of many insights related to service provision in the airway industry, management of digital support channels, management of reputation on social media and using Twitter as a customer support platform.

Relevant share tweets comprise only 20% of all share tweets for one company and show the same level of correlation with stock performance. This means that the efficiency of business intelligence solutions created to monitor Twitter activity can be improved five times by saving computational power, network bandwidth and data storage.

Previous research has analyzed all Twitter activity taken together. By dividing tweets into semantic and share tweets, this paper illustrates that it is, in fact, share tweets that are correlated with stock performance and not semantic tweets.

The purpose of this paper is to investigate the types of roles that Twitter played in digital libraries (DLs) and their relationships in building DL online communities.

A mixed method analysis of DLs’ tweets was conducted to identify the usage, roles of Twitter in DL communities and relationships among the roles. Twitter data from 15 different DLs for one year were extracted, and an open coding analysis was performed to identify types of Twitter roles. Pearson correlation coefficient was applied to examine the relationships among the roles based on word similarities.

The results present 15 types of Twitter roles representing five main categories identified from DL tweets, including information, promotion, related resources, social identity and social connection. Moreover, word similarities analysis identifies more strong relationships among the roles in four main categories (promotion, related resources, social identity and social connection) but less with roles in information.

Characteristics of DL online communities are discussed and compared with physical library communities. Suggestions are proposed for how tweets can be improved to play more effective roles. To build a strong community, it is critical for digital librarians to engage with followers.

This study is a pioneering work that not only analyzes Twitter roles and their relationships in building DL online communities but also offers recommendations in terms of how to build a strong online community and improve Twitter use in DLs.

Despite rapid growth in organizational use of Twitter, there is little theoretical or empirical research examining how different organisations use Twitter. This paper aims to analyse and compare use of Twitter in 12 accounts held by six organisations in the USA and Australia, drawing on existing models of interactive communications.

The paper is based on analysis of a random sample of tweets sent by each account.

The results demonstrate different ways in which the interactive capabilities of Twitter can be used to communicate with customers. However by also demonstrating lack of consistency in Twitter practice within most organisations, the results reinforce the need for strategic consistency in developing Twitter practice.

The results are based on the Twitter practice of 12 organisational accounts in the USA and Australia from December 2009 to May 2010. As with any evolving medium, practices at the different organisations may have changed since that time.

The paper is the first to compare Twitter use within and across organisations and geographic markets. It demonstrates a variety of potential Twitter practices, and discusses the advantages and disadvantages of different strategies, and thus provides a framework for analysis of Twitter practice, and strategic direction for organisations developing their use of Twitter. The paper identifies challenges in the use of Twitter as both a one‐to‐many, and also a one‐to‐one, communication medium, and suggests strategies for coping with this dual use of Twitter.