Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

Data Science for Influencer Marketing : feature processing and quantitative analysis

Anil Narassiguin 1, 2 Selina Sargent 2 
1 DM2L - Data Mining and Machine Learning
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Influencing a target audience through social media content has become a new focus of interest for marketing leaders. While a large amount of heterogeneous data is produced by influencers on a daily basis, professionals in the influ-encer marketing (IM) field still rely on simple quantitative metrics such as community size or engagement rate to estimate the value of an influencer. As few research papers have proposed a framework to quantify the performance of an influencer by using quantitative influencer data (number of followers, engagement,...), qualitative information (age, country, city, etc...), natural text (profile and post descriptions) and visual information (images and videos), we decided to explore these variables and quantitatively evaluate their dependencies. By analyzing 713,824 influencers on 5 social media platforms over a period of one year, we identified relationships between value proposition data (engagement, reach, audience), demographics, natural text patterns and visual information. The main goal of this paper is to provide IM professionals with a modern methodology to better understand the value of their influencers and to feed machine learning algorithms for clustering, scoring or recommendation.
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download
Contributor : Anil Narassiguin Connect in order to contact the contributor
Submitted on : Monday, May 6, 2019 - 11:35:17 AM
Last modification on : Friday, September 30, 2022 - 11:34:16 AM


Files produced by the author(s)


  • HAL Id : hal-02120859, version 1
  • ARXIV : 1906.05911


Anil Narassiguin, Selina Sargent. Data Science for Influencer Marketing : feature processing and quantitative analysis. {date}. ⟨hal-02120859⟩



Record views


Files downloads