Title

Assessing Consumer Sentiment When Using Instagram as a Marketing Platform

Author(s)

Khushi Dave

School Name

Spring Valley High School

Grade Level

12th Grade

Presentation Topic

Consumer Science

Presentation Type

Non-Mentored

Abstract

As Instagram grows to be the number one social media platform, companies are taking advantage of its popularity by promoting their products through the use of social media influencers. Using influencers has become an increasingly popular marketing strategy, and therefore the purpose of this study was to analyze consumer sentiment for this method of advertising. It was hypothesized that if social media influencers post sponsored advertisements, then those posts would be less favored than non-sponsored posts made by the influencer. It was also hypothesized that as the popularity of the influencer increases, then consumer sentiment would become more negative. The research was conducted using sentiment analysis, a data mining technique that uses natural language processing to identify the content of interest from textual data. Instagram comments were analyzed for a sentiment score from -1 to 1, 0 being neutral and becoming increasingly negatively or positively polar as they approach 1. The number of likes was also recorded, expressed as a proportion based on the number of followers the influencer has. It was seen that sentiment was relatively equal between sponsored and non-sponsored posts. The sentiment scores were also seen to decrease as popularity increased. Two one-sample t-tests supported this, showing that there is no significant difference between sponsored and non-sponsored posts. Two ANOVAs and their subsequent Scheffé test showed that there is a significant difference in sentiment as popularity increases. This partially supports the hypothesis, showing that consumers prefer advertisements made by smaller influencers.

Location

Furman Hall 110

Start Date

3-28-2020 9:00 AM

Presentation Format

Oral and Written

Group Project

No

COinS
 
Mar 28th, 9:00 AM

Assessing Consumer Sentiment When Using Instagram as a Marketing Platform

Furman Hall 110

As Instagram grows to be the number one social media platform, companies are taking advantage of its popularity by promoting their products through the use of social media influencers. Using influencers has become an increasingly popular marketing strategy, and therefore the purpose of this study was to analyze consumer sentiment for this method of advertising. It was hypothesized that if social media influencers post sponsored advertisements, then those posts would be less favored than non-sponsored posts made by the influencer. It was also hypothesized that as the popularity of the influencer increases, then consumer sentiment would become more negative. The research was conducted using sentiment analysis, a data mining technique that uses natural language processing to identify the content of interest from textual data. Instagram comments were analyzed for a sentiment score from -1 to 1, 0 being neutral and becoming increasingly negatively or positively polar as they approach 1. The number of likes was also recorded, expressed as a proportion based on the number of followers the influencer has. It was seen that sentiment was relatively equal between sponsored and non-sponsored posts. The sentiment scores were also seen to decrease as popularity increased. Two one-sample t-tests supported this, showing that there is no significant difference between sponsored and non-sponsored posts. Two ANOVAs and their subsequent Scheffé test showed that there is a significant difference in sentiment as popularity increases. This partially supports the hypothesis, showing that consumers prefer advertisements made by smaller influencers.