Social Media Sentiment Analysis, and Soccer
What is social media sentiment analysis?
Before delving into the nitty gritty of exactly how sentiment analysis works, let’s break the concept down into something a little more tangible, shall we. Have you ever wondered what the South African public thought about, let’s say, Iceland’s football team defeating England in the Euro 2016? Well, that right there my friends, is why sentiment analysis software exists – to make vast quantities of data easily understandable at a glance. Think of it like a snapshot of the emotional response to a given topic.
You might be asking yourself, but what about online surveys and polls, isn’t that their purpose? Well, yes, but while Facebook and Twitter polls have been used successfully to glean feedback on products and services the world over, they harbor two inherent flaws. 1) Unless it’s a topic really close to the respondent’s heart, typically, people aren’t massive fans of completing polls and surveys. 2) The validity of a poll is contingent on your sample size, and it’s not always easy to cultivate an online following the size of a country. With sentiment analysis software you’re able to circumvent both of those obstacles by listening into people’s organic conversations, and on a scale far grander than any poll’s ever managed.
How does sentiment analysis software work?
At its heart, Meltwater’s sentiment analysis software is founded on what’s known as Natural Language Processing, or NLP, for short. The aim of NLP in its simplest form is to learn whether the writer is more for, or against, the topic he or she writes about – so, do they like or dislike the subject? Most sentiment extraction tools assign a single numeric score, e.g. a value in the range from -1 to 1, that represents the author’s attitude or overall evaluation. Meltwater’s current sentiment extraction solution is one such system. So, in keeping with the Euro 2016 theme, let’s take a look at the following sentence:
“Loved the epic shot Kolbeinn Sigþórsson slipped past Joe Hart’s fingertips.”
When encountering the above text, NLP systems would search their own internal databases and (if they’re worth their salt) attribute positive values to words like “love” and “epic”, changing the overall sentiment of the statement to positive. While not without its own limitations (such as interpreting sarcasm and emojis) sentiment analysis software provides an effective way of looking through vanity metrics like total likes, and helps users actually understand contextual insights.
Sentiment analysis and business
The application of sentiment analysis software at a business level is manifold: extending all the way from understanding how consumers feel about your last campaign, to tracking shifts in the political landscape. History has taught us that consumers don’t always respond the way you want them to, and keeping your finger on the pulse ensures you’re able to react before it’s too late.
In the curious case of Iceland vs England for example, we saw more of the South African public choosing to view the Icelandic underdogs’ victory in a positive light (green line), than negative (red line). So, from a purely data driven perspective, South Africans would like to say: “Gangi þér vel, Iceland”, or otherwise phrased, good luck!
Want to measure your brand’s online sentiment? Connect with us now.