Enhancing Marketing Intelligence with Sentiment Analysis
A case study of three UK fast fashion brands
This is the fourth of a research summary series which was initiated to bring to the limelight the academic studies done on data science in the context of the fashion industry.
Episode Four is a review of the paper titled “Making sense of consumers’ tweets: Sentiment outcomes for fast fashion retailers through Big Data analytics”.
Follow and subscribe to get article updates.
Offering fashionable fashion goods, fantastic discounts, or intriguing marketing efforts is not enough to boost fashion consumer satisfaction. Therefore, as a fashion merchant, you should explore understanding customer opinions about your brand in order to meet their needs while remaining profitable in today’s competitive environment.
In general, some consumers offer their thoughts on fashion items they purchased and how they made them feel, or they share their experience with a brand. Such opinions may be found on review sites, your website, social media platforms, blogs, and so on.
As such, in order to boost customer satisfaction, you must first understand how they perceive your brand. To do so, you may leverage customer data from social media and all of the channels I mentioned earlier, perhaps more. This is when sentiment analysis comes into play.
Sentiment Analysis may aid you in extracting and quantifying customer comments and thoughts about your brand, offering important insights into their preferences as well as supporting you in identifying probable reasons impacting their opinions.
In this blog post, I am going to review a research paper on analysing consumer tweets about three fast fashion retailers, but first, let me define sentiment analysis.
What is Sentiment Analysis?
Sentiment analysis is a subset of Text Analysis that assists you in gaining meaningful insights from qualitative and unstructured data, such as tweets.
The goal of sentiment analysis is to identify the attitude, opinion, or emotion expressed in a piece of text on for instance, Twitter, as a result,it allows you to learn how your customers feel about their interactions with your business.
Interested in knowing what the research authors did?
Keep reading…
The purpose of the study was to use sentiment analysis to enhance marketing intelligence by analysing text content that internet users provide. The authors considered a case study using three fast-fashion retailers operating in the UK market.
Several studies, according to the authors, have investigated the role of online consumers’ content in terms of ratings, photographs, and reviews that include consumer opinions and recommendations, and these are frequently spread throughout social media and online platforms such as e-commerce, bookings, product or activity reviews, etc.
Therefore, marketers are privy to a large amount of data that can be used to improve decision-making processes by influencing competition and marketing intelligence.
However, there have been few attempts in the past to research the role of consumer-generated content from a marketing viewpoint in order to support marketing intelligence.
For this reason, the authors of this research aimed to contribute to understanding customers’ online content in terms of positive or negative remarks in order to boost marketing intelligence. They used a sentiment analysis based on machine learning to collect and analyse 9,652 tweets from three fast fashion retailers operating in the UK market.
In the following paragraphs, I will highlight a few works of literature as well as the authors' research significance.
Grab your coffee!
Literature Review
As opposed to waiting a long time for a collection to be manufactured and distributed in stores after showcasing on the runway, resulting in a prolonged season and making the consumers wait a long time for the clothes to be available in stores. Fast fashion retailers provide the most updated high-end fashion products (collections that mimic current luxury fashion trends) at low prices available for consumers every few weeks instead of every season as for luxury brands.
In other words, fast fashion retailers have reduced the length of each season by providing different fashion products and altering the products they offer regularly in order to entice customers to return to the store.
This, in turn, shortens the life cycle of such products (limited time from introduction to decline) (Barnes and LeaGreenwood, 2010) and leads customers to believe that fast fashion items are only accessible in limited quantities (Cook and Yurchisin, 2017).
What a strategy!
Due to the necessity to release new items quickly and sell them while trends are in vogue, fast fashion shops must employ quick response systems and flexible supply chain management (Cook and Yurchisin, 2017).
The bottom line is that maintaining that strategy will not only benefit these fast fashion retailers but will also present a few challenges for them. Furthermore, studies have found that there are two main components that contribute to establishing long-term relationships between fast fashion retailers and consumers:
- Internet word-of-mouth (eWOM) communication and user-generated content (UGC)
- Celebrity endorsement.
In general, eWOM and user-generated content (UGC) emerge as important drivers of consumer purchasing decisions, and this has led to several studies investigating the effects of these drivers on sales or identifying the effect of positive or negative online comments, posts, or reviews.
With respect to fast fashion, previous studies have investigated the fast fashion industry by focusing primarily on supply chain and consumer behavioural models tested with traditional surveys limited to a specific sample of the population (i.e., college students), without effectively investigating online consumers’ behaviour towards those retailers in terms of user-generated content and e-word-of-mouth communications.
To fill this research gap, the authors of this study chose a multiple case study approach to explore consumers’ online-generated content and the impact of positive or negative comments on marketing intelligence.
Want to know what these authors did and their findings?
Read the full paper HERE
Hope you enjoyed reading the article as much as I enjoyed writing it. Don’t forget to drop your feedback in the comment session.
Connect with me on LinkedIn.
CHEERS!
Subscribe to my weekly LinkedIn Newsletter, Data Literacy Explained, to increase your data literacy—the understanding, interpretation, and communication of data.
