Predicting consumers engagement on Facebook based on what and how companies write

Issue title: Special section: Selected papers of LKE 2019

Guest editors: David Pinto, Vivek Singh and Fernando Perez

Article type: Research Article

Authors: Rosas-Quezada, Érika S.^a | Ramírez-de-la-Rosa, Gabriela^a | Villatoro-Tello, Esaú^{a; b; *}

Affiliations: [a] Language and Reasoning Research Group, Information Technologies Department, Universidad Autónoma Metropolitana, Cuajimalpa, Mexico | [b] Idiap Research Institute, Rue Marconi 19, Martigny, Switzerland

Correspondence: [*] Corresponding author. Esaú Villatoro-Tello. E-mails: [email protected] and [email protected].

Abstract: Engaged customers are a very import part of current social media marketing. Public figures and brands have to be very careful about what they post online. That is why the need for accurate strategies for anticipating the impact of a post written for an online audience is critical to any public brand. Therefore, in this paper, we propose a method to predict the impact of a given post by accounting for the content, style, and behavioral attributes as well as metadata information. For validating our method we collected Facebook posts from 10 public pages, we performed experiments with almost 14000 posts and found that the content and the behavioral attributes from posts provide relevant information to our prediction model.

Keywords: Social media branding, impact analysis, data mining, features engineering, natural language processing

DOI: 10.3233/JIFS-179897

Journal: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 2, pp. 2365-2377, 2020