Which social media posts generate the most buzz? Evidence from WeChat

Abstract

PurposeFollowing the hierarchy-of-effects model, this study aims to propose a two-step process framework to investigate social media post efficacy via attraction and likes.Design/methodology/approachThe study analyzes 113,785 social media posts from 126 WeChat official accounts to explore how external (headline features and account type) and internal (content features and media type) features impact social media post attractions and likes, respectively.FindingsThe antecedents of post attraction differ from those of post likes. First, headline features (punctuation, length, sentiment and lexical density) and account type significantly influence social media post attraction. Second, content features (depth, tone, domain specificity, lexical density and readability) and media type affect social media post likes.Originality/valueFirst, this study considers online user engagement as a two-step process regarding social media posts and explores different influencing factors. Second, the study constructs new variables (account type and domain specificity) in each stage of the two-step process model.

A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts

“…Together with the interplay between technology and modernization, their impact has also extended to social media. For instance, scholars have pointed out that shorter posts typically lead to a higher engagement rate on Facebook (Sabate et al, 2014), potentially because concise messages reduce the amount of cognitive effort needed for information processing (She et al, 2022). Across the various available types of platforms, Twitter, in particular, restricts each post to a maximum of 280 characters (Queiroz, 2018), and although these short and unstructured posts conform with social media practice, they increase the complexity for algorithms to make sense of digital interaction.…”

How online reviews with different influencing factors affect the diffusion of new products

“…Emotional tendency analysis is a computational approach for identifying the positive or negative sentiment of online reviews through text mining techniques (She et al, 2022). According to the accessibility‐diagnostic model, reviews with emotional tendencies are more valuable in helping consumers identify and infer the performance of products than neutral reviews that tend to contain ambiguous information (Zhu et al, 2022).…”

Online Health Information Wants of Caregivers for Persons With Dementia in Social Media

“…Prior studies have shown that the length of a social media post can affect its attraction to the audience, but the findings are inconclusive (She et al, 2022;). For instance, She et al (2022) and Hudson (2016) found that the longer the post the less attractive to the readers and speculated that the comprehension challenge being an important reason. Antoniadis et al (2019) analyzed retail brand pages on Facebook and found that the length of a post has a weak positive effect on the post's popularity.…”