Sell-Bot: An Intelligent Tool for Advertisement Synthesis on Social Media

Sonny Kabaso, Abejide Ade-Ibijola

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

3 Citations (Scopus)

Abstract

Social Media Advertising is one of the fastest ways to reach a large group of targeted customers. In the present day, there are large volumes of advertisement campaigns designed for, and running on Social Media Platforms, yielding significant conversion rates for businesses. Advances in Artificial Intelligence (AI) have offered new techniques for tailoring advertisements towards targeted audiences. Some of these techniques include Machine Learning (ML) applications in the analysis of Big Data; acquired from customers spending, and/or buying patterns. Hence, software companies and researchers have created several tools that target specific customers in need of specific products and services. An aspect of AI that has not seen too many applications in Advertising is Natural Language Generation (NLG); the study of algorithms for generating natural or human languages. In this chapter, we present a NLG algorithm for the automatic generation of advertisements for Social Media platforms. This algorithm is implemented in a tool called Sell-Bot that is based on Context-free Grammars; a formal technique for describing or generating languages. This algorithm takes a list of available and currently discounted commercial products and services of an organisation, and intelligently composes a valid Social Media post (a tweet or Facebook post) that is often indistinguishable from a human expert marketer’s tweet or post. An evaluation of Sell-Bot showed that 42% of the participants did not know whether the AI (Sell-Bot) or the human generated the adverts. Sell-Bot is expected to relieve humans of their efforts of posting advertisements on Social Media.

Original languageEnglish
Title of host publicationLecture Notes in Electrical Engineering
PublisherSpringer
Pages155-178
Number of pages24
DOIs
Publication statusPublished - 2020

Publication series

NameLecture Notes in Electrical Engineering
Volume674
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Keywords

  • Advert synthesis
  • Advertising
  • Context-free grammar
  • Natural language generation
  • Procedural generation
  • Social media
  • Synthesis of things

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Sell-Bot: An Intelligent Tool for Advertisement Synthesis on Social Media'. Together they form a unique fingerprint.

Cite this