TY  - BOOK
AU  - Agozie,Divine Quase
AU  - Nat,Müesser
TI  - A LATENT FIRICHLET ALLOCATION ANALYSIS OF ORGANIZATIONAL COMMUNICATION IN TWITTER
PY  - 2023///
KW  - Communication in organizations
KW  - Dissertations, Academic
KW  - Social media
N1  - Thesis (PhD) - Cyprus International University. Institute of Graduate Studies and Research management Information Systems Department; Includes bibliography (sheets 124-141)
N2  - ABSTRACT 
Sustained engagement with an audience remains a need for organizations, and many 
organizations have sourced technology-mediated channels, like social media, to 
achieve this objective in recent. Although not a recent concept, organizational 
communication online has received much recognition with the rise in the 
organizational use of online channels like social media for communication and 
providing value experience to users. The value experience perceived by users and the 
extent of interactivity on social media show how engaging audiences are. Few studies 
have looked at what drives this value experience in organizational communication. 
This study explores the role of message features and the functional use of posts by 
interest groups and discerns their effect on user engagement with and without 
multimedia inclusion on Twitter. A bi-term topic modelling technique is used to 
analyze posts from 323 organizations, and a Poisson regression model to assess the 
effect of the message features (Technical characteristics, User and Network 
characteristics and Content characteristics) and the content functions on user 
engagement. The results show that technical characteristics like images and word 
length of posts increased engagement. User and network characteristics as followers 
and type of group are the most important characteristics that drive engagement. 
Content functions including information, research, community, and news functions of 
posts also increased user engagement with organizational messages. This study bridges 
the gap in the service literature as it pertains to non-profit organizations (i.e., interest 
groups) by exploring organizational communication using communications content 
functions and message characteristics of Twitter posts. This study is among few to 
investigate content functions beyond the categorizations of message functions and the 
relationship between content functions and user engagement. 
Keywords: Latent Dirichlet Allocation, Organizational communication, Poisson 
regression model, Social-media, Twitter, User engagement.
ER  -