{"title":"利用监督机器学习研究社交媒体上的战略多样性交流:开发、验证和未来研究方向","authors":"Joep Hofhuis , João Gonçalves , Pytrik Schafraad , Biyao Wu","doi":"10.1016/j.pubrev.2024.102431","DOIUrl":null,"url":null,"abstract":"<div><p>In this paper, we present a digital tool named <em>Diversity Perspectives in Social Media</em> (DivPSM) which conducts automated content analysis of strategic diversity communication in organizational social media posts, using supervised machine-learning. DivPSM is trained to identify whether a post makes mention of diversity or a diversity-related issue, and to subsequently code for the presence of three diversity dimensions (cultural/ethnic/racial, gender, and LHGBTQ+ diversity) and three diversity perspectives (the moral, market, and innovation perspectives). In Study 1, we describe the training and validation of the instrument, and examine how it performs compared to human coders. Our findings confirm that DivPSM is sufficiently reliable for use in future research. In study 2, we illustrate the type of data that DivPSM generates, by analyzing the prevalence of strategic diversity communication in social media posts (<em>n</em> = 84,561) of large organizations in the Netherlands. Our results show that in this context gender diversity is most prevalent, followed by LHGBTQ+ and cultural/ethnic/racial diversity. Furthermore, gender diversity is often associated with the innovation perspective, whereas LHGBTQ+ diversity is more often associated with the moral perspective. Cultural/ethnic/racial diversity does not show strong associations with any of the perspectives. Theoretical implications and directions for future research are discussed at the end of the paper.</p></div>","PeriodicalId":48263,"journal":{"name":"Public Relations Review","volume":"50 1","pages":"Article 102431"},"PeriodicalIF":4.1000,"publicationDate":"2024-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0363811124000109/pdfft?md5=8db86f796719a420acecfa9ceca0512c&pid=1-s2.0-S0363811124000109-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Examining strategic diversity communication on social media using supervised machine learning: Development, validation and future research directions\",\"authors\":\"Joep Hofhuis , João Gonçalves , Pytrik Schafraad , Biyao Wu\",\"doi\":\"10.1016/j.pubrev.2024.102431\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In this paper, we present a digital tool named <em>Diversity Perspectives in Social Media</em> (DivPSM) which conducts automated content analysis of strategic diversity communication in organizational social media posts, using supervised machine-learning. DivPSM is trained to identify whether a post makes mention of diversity or a diversity-related issue, and to subsequently code for the presence of three diversity dimensions (cultural/ethnic/racial, gender, and LHGBTQ+ diversity) and three diversity perspectives (the moral, market, and innovation perspectives). In Study 1, we describe the training and validation of the instrument, and examine how it performs compared to human coders. Our findings confirm that DivPSM is sufficiently reliable for use in future research. In study 2, we illustrate the type of data that DivPSM generates, by analyzing the prevalence of strategic diversity communication in social media posts (<em>n</em> = 84,561) of large organizations in the Netherlands. Our results show that in this context gender diversity is most prevalent, followed by LHGBTQ+ and cultural/ethnic/racial diversity. Furthermore, gender diversity is often associated with the innovation perspective, whereas LHGBTQ+ diversity is more often associated with the moral perspective. Cultural/ethnic/racial diversity does not show strong associations with any of the perspectives. Theoretical implications and directions for future research are discussed at the end of the paper.</p></div>\",\"PeriodicalId\":48263,\"journal\":{\"name\":\"Public Relations Review\",\"volume\":\"50 1\",\"pages\":\"Article 102431\"},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2024-02-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0363811124000109/pdfft?md5=8db86f796719a420acecfa9ceca0512c&pid=1-s2.0-S0363811124000109-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Public Relations Review\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0363811124000109\",\"RegionNum\":3,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BUSINESS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Public Relations Review","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0363811124000109","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BUSINESS","Score":null,"Total":0}
Examining strategic diversity communication on social media using supervised machine learning: Development, validation and future research directions
In this paper, we present a digital tool named Diversity Perspectives in Social Media (DivPSM) which conducts automated content analysis of strategic diversity communication in organizational social media posts, using supervised machine-learning. DivPSM is trained to identify whether a post makes mention of diversity or a diversity-related issue, and to subsequently code for the presence of three diversity dimensions (cultural/ethnic/racial, gender, and LHGBTQ+ diversity) and three diversity perspectives (the moral, market, and innovation perspectives). In Study 1, we describe the training and validation of the instrument, and examine how it performs compared to human coders. Our findings confirm that DivPSM is sufficiently reliable for use in future research. In study 2, we illustrate the type of data that DivPSM generates, by analyzing the prevalence of strategic diversity communication in social media posts (n = 84,561) of large organizations in the Netherlands. Our results show that in this context gender diversity is most prevalent, followed by LHGBTQ+ and cultural/ethnic/racial diversity. Furthermore, gender diversity is often associated with the innovation perspective, whereas LHGBTQ+ diversity is more often associated with the moral perspective. Cultural/ethnic/racial diversity does not show strong associations with any of the perspectives. Theoretical implications and directions for future research are discussed at the end of the paper.
期刊介绍:
The Public Relations Review is the oldest journal devoted to articles that examine public relations in depth, and commentaries by specialists in the field. Most of the articles are based on empirical research undertaken by professionals and academics in the field. In addition to research articles and commentaries, The Review publishes invited research in brief, and book reviews in the fields of public relations, mass communications, organizational communications, public opinion formations, social science research and evaluation, marketing, management and public policy formation.