Feature Bundle – Text Analysis for Social Listening
Social media is a gold mine of useful information and public opinion that is just waiting to be tapped. Right now, millions of people on social channels are talking about an immeasurable range of topics, people and organizations, all the while making their valuable opinions public and accessible.
From a marketing point of view as an organization or brand, you want to know what is being said about you (and your competitors) on social media, and how it is being said. This is no easy task, as the number of channels and sheer amount of data online continue to explode.
Enter Social Listening and Text Analysis.
Social listening involves monitoring the web and the social media channels to see what’s being said about your brand, your competitors, your industry and other key areas of interest to you. But simply listening isn’t always enough. We want to understand what we are hearing out there.
How can Text Analysis help?
Using Machine Learning and Natural Language Processing techniques, it’s easier than ever to understand and analyze social media content at scale.
To make things easy for you, we’ve put together a list of Text Analysis features (or endpoints as we call them) that are being widely used by our customers for social listening. So if you’re new to using our API this will help you get up to speed quickly.
- Entity & Concept Extraction
- Sentiment Analysis
- Aspect-Based Sentiment Analysis
Note: We have a really cool and easy-to-use Demo showcasing all of these features. You can test them out with your own text data (articles, tweets URLs etc) or try some of our sample queries.
Let’s begin by taking a look at the first feature on our list, extracting entities and concepts.
1. Entity & Concept Extraction
Social content contains a wealth of mentioned entities and values that can provide some really interesting and important information. The challenge is mining this information, particularly at scale. To best understand social content, you want to know the who, the what and the how much from each and every post or update.
Entity Extraction extracts named entities (people, organizations, products and locations) and values (URLs, emails, telephone numbers, currency amounts and percentages) mentioned in a body of text or web pages.
Concept Extraction extracts named entities mentioned in social posts and cross-links them to DBpedia and Linked Data entities, for greater understanding.
Concept extraction also disambiguates similarly named entities. Take Apple for example. If it is mentioned in an article is it a reference to the company or the fruit? Concept extraction analyzes the content around the word and through Machine Learning and Natural Language Processing (NLP) techniques, performs the disambiguation.
By extracting entities and concepts from social content and analyzing at scale you can gain some incredibly useful insights and get answers to key questions, such as;
- What else are people talking about when they mention our brand/product/competitor?
- What words, phrases, brands etc are mentioned most?
- Are they mentioning or comparing us to other brands?
- Are they mentioning specific people or places in relation to our brand/product/competitor?
Here’s a great example from our analysis of the Super Bowl ads battle, where we collected 120,000 tweets that mentioned, or were related to, the brands that advertised during Super Bowl 50. By listening for specific mentions of entities and concepts, you can see trends over time and pinpoint reasons for them. The spike in the center of the graph below is during the game itself, when Twitter chatter is naturally going to be at its peak. One interesting observation we made here was Budweiser’s (red) sudden sharp rise in mentions after an otherwise comparatively quiet event. Upon further investigation, we discovered that Peyton Manning had mentioned the brand, ad-lib, live on air. It’s amazing what a single celebrity mention can do for your brand! And from a marketing/social-listening perspective, it’s amazing to see this information as it happens.
The graph below is interactive so you can hover over it for more information.
Because we listened out for 15 of the top brands that advertised during the event, we were able to dive deeper to gather further brand-specific insights. The clusters below represent the most-used words in tweets mentioning Amazon. Think of how useful this visualization would be for your own marketing efforts.
As you can see, Entity & Concept Extraction can be an extremely powerful tools in your social-listening arsenal. Now we’ll take a look at how you can gauge the sentiment of social media posts – are they written in a positive or negative way?
2. Sentiment Analysis
Brand awareness and reputation are extremely important to any organization. It is therefore essential to listen to how people are talking about you on social media, whether it is relating directly to your brand, one of your products or services, or even your competitors. You want to know whether they are mentioning each of these in a positive or negative way. You want to hear the true voice of the customer. This is where Sentiment Analysis comes in.
Sentiment Analysis detects the sentiment of a social post in terms of polarity (positive or negative) and subjectivity (subjective or objective). When used, particularly at scale, it can show you how people feel towards the topics that are important to you.
Analyzing the sentiment towards your brand can help you decrease churn and improve customer support by uncovering and proactively working on improving negative trends. It can help show you what you are doing wrong before too much damage has been done, but also quickly show you what you are doing right and should therefore continue doing. Sentiment Analysis can also be used to analyze your competitors social media presence and performance. You can learn from both their social media triumphs and disasters and use this information to improve your own campaigns.
Wanna know how the public feels about your latest ad? Let’s go back to our Super Bowl analysis and look at two brands who at either end of the polarity scale – Amazon and PayPal.
In the graphs below, green represents positive sentiment and red represents negative. As you can see, Amazon’s ad was very well received. PayPal’s certainly wasn’t!
Sentiment Analysis is an essential part of social listening and plays an important role in understanding the voice of the customer. But what if we want to go a step further and discover what aspects the positive/negative sentiment is stemming from? What exactly do our customers like or dislike about us?
To answer these questions, we developed Aspect-Based Sentiment Analysis.
3. Aspect-Based Sentiment Analysis
While Sentiment Analysis provides fantastic insights and has a wide range of real-world applications, the overall sentiment of a social post won’t always pinpoint the root cause of the author’s opinion.
This is where Aspect-Based Sentiment Analysis (ABSA) comes in. With ABSA, you can dive deeper and analyze the sentiment of social content toward industry-specific aspects.
Social media content, such as tweets, facebook posts and reviews, may contain fine-grained sentiment about different aspects (e.g. a product or service) that are mentioned in the content. For instance, a review about a restaurant may contain opinionated sentences about its staff, location, food, drinks and value. This information can be highly valuable for understanding customers’ opinion about a particular service or product.
As a restaurant owner, let’s say I have received 700 online reviews that result in an overall review score of 8/10. I’m quite happy with this but clearly there is room for improvement. But where exactly? By running the customer reviews through our ABSA endpoint, I can immediately start to see what my customers like, and more importantly dislike. As an example, we analyzed a 5-star restaurant review and got the following results;
We visited here during our recent trip to Sydney and overall we were very impressed. We decided to make a reservation online, which was quick and easy with instant confirmation. It was nice to be able to view the table layout and select our own online. The location is spectacular with stunning views of the harbour and Opera House. It truly was amazing. Despite this, however, the restaurant was only about 25% full and so the atmosphere was a bit flat. Perhaps this was to our benefit as we received top class service from our waiter, Brandon, who was not only friendly and funny but extremely knowledgeable when it came to food and wine pairings. Speaking of wine, the list was extensive – we loved it – and it took us what seemed like an hour to eventually decide on a local Shiraz. Now on to the most important aspect, the food. Our seafood starters were delicious, as were out fillet steak mains. The one and only real disappointment was the dessert which was served with no real imagination and looked like it had been purchased yesterday at the local grocery store. All in all, my favourite Sydney restaurant so far. So many positives and really good value too. Highly recommend!
As you can see from the results above, the ABSA endpoint automatically pulls industry-specific aspects (such as food, drinks, reservations and value), performs Sentiment Analysis on each aspect and gives sample sentences to indicate examples of where the the score was derived.
Although this review was extremely positive and received a 5-star rating, we can still uncover certain aspects that may be in need of improvement. Our customer was clearly not impressed with their dessert and also found the general atmosphere of the restaurant to be a bit flat.
ABSA is currently available for four industries – Airlines, Hotels, Cars and Restaurants – and we are already working on expanding this list. Here are the aspects covered for our initial four industries;
We hope this post gives you some inspiration and helps you to understand the various Text Analysis features available to you and how they can help you with your social listening efforts.