A Sentimental Analysis Tool for Determining the Promotional Success of Fashion Images on Instagram

Conference item


Tallent, G, Galal, D and Abdelfattah, M (2016). A Sentimental Analysis Tool for Determining the Promotional Success of Fashion Images on Instagram. 1st BUE Annual Conference & Exhibition. Cairo, Egypt 07 - 09 Nov 2016 London South Bank University.
AuthorsTallent, G, Galal, D and Abdelfattah, M
Abstract

Sentiment Analysis (SA) or Opinion Mining is the process of analysing natural language texts to detect anemotion or a pattern of emotions towards a certain product to make a decision about that product. SA is atopic of text mining, Natural Language Processing (NLP) and web mining disciplines. Research in SA iscurrently at its peak given the amount of data generated from social media networks. The concept is thatconsumers are expressing exactly what they need, want and expect from a product but on the other hand thecompanies don’t have the tools to analyse and understand these feelings to satisfy these consumersaccordingly.One of the applications that generate a high rate of reactions and sentiments in social networks isInstagram. This study focuses on analysing the reactions generated by the top 50 fashion houses on Instagramgiven their top 20 images with the highest number of likes. The approach taken in this study is to qualify thevisual aesthetics of fashion images and to establish why some succeed on social media more than others.The basic question asked in this paper is whether there are certain visual aesthetics that appeal more to theuser and are therefore more successful on social media than others as determined by a measure we introduce,‘Social Value’. To do so, a sentiment analysis tool is developed to measure the proposed social value of eachimage. An input of comments from each image will be processed. Each comment will go through a preprocessingphase; each word will be placed through a lexicon to identify if it is positive or negative. Theoutput of the lexicon is a score value assigned to each comment to identify its degree of positivity, negativity,or it has no effect on the social value. Adding to these results, the number of likes and shares would also betaken into consideration quantifying the image’s value. A cumulative result is then produced to determine thesocial value of an image. Keywords: Sentiment Analysis; Opinion Mining; Instagram; Social Value; Aesthetics

Year2016
PublisherLondon South Bank University
Accepted author manuscript
License
CC BY 4.0
Publication dates
Print07 Nov 2016
Publication process dates
Deposited12 Jan 2017
Accepted07 Nov 2016
Permalink -

https://openresearch.lsbu.ac.uk/item/871q9

  • 5
    total views
  • 11
    total downloads
  • 2
    views this month
  • 4
    downloads this month

Related outputs

The Social Media Canvas and Its Use in Strategy Formulation
Tallent, G (2014). The Social Media Canvas and Its Use in Strategy Formulation. European Conference on Social Media ECSM. Brighton UK 10 - 14 Jul 2014 London South Bank University.
Integrating Social Media into the Business Strategy of an Organisation
Tallent, G (2014). Integrating Social Media into the Business Strategy of an Organisation. Proceedings of 3rd European Business Research Conference. Rome, Italy 04 - 05 Sep 2014 London South Bank University.
The Strategic Use of Instagram in the Fashion Industry
Tallent, G (2016). The Strategic Use of Instagram in the Fashion Industry. Business in a Dynamic World conference. Limassol, Cyprus 15 - 17 Jan 2016 London South Bank University.