Sentiment Analysis Brings Restaurant Insights to Your Table

The US restaurant industry is a thriving one with an estimated revenue of $799 billion in 2017. It is also a competitive industry for both chain and non-chain restaurants. Understanding what customers enjoy and value about one’s establishments over its competitors is critical for a restaurant business and brand to thrive.

The good (and sometimes not so good) news is that restaurant goers love to leave reviews online, whether it’s on Yelp, OpenTable, TopTable, TripAdvisor, Facebook, Instagram, and others. Restaurant goers also love to read online restaurants reviews, especially millennials. According to a study, 61% of customers have read online reviews about restaurants and 53% percent of the coveted 18 to 34-year-old demographic are heavily influenced by reviews when making dining decisions.

It’s not just the quality of food that people write about. There are so many other aspects to the restaurant experience that are commented on. Here is a taste:

• Portions (“Huge helpings”, “The Reuben was enormous”, “hearty portions”, “the servings were humongous”)
• Menu options (“Many choices on menu for all tastes”, “Really interesting menu”, “Lots of variety”, “They have a pretty extensive menu”)
• Service (“The service was excellent”, “Friendly and quick service!”, “The server was not very attentive”)
• Promptness (“Our food came out in a timely manner”, “All of our food came quickly”, “After ordering, we waited 70 minutes”)
• Food quality (“Potatoes disappoint, consistently underseasoned and underdone”, “The Duck salad was phenomenal”, “Their burgers are cooked perfectly”, “Sandwiches here are just outstanding”, “My Filet was awful”)
• Pricing (“Reasonably priced”, “The prices were a bit steeeeeep”, “It is pricier than most”)
• Wait time (“Generally do not have to wait long for a table”)
• Noise level (“The noise level was so high that we couldn’t hear each other talk”)
• Parking (“Parking can be an issue”, “Close to parking in the heart of Catonsville”)
• Intent to return (“We’ll most likely return”, “Will not be back”, “Will return many times”)
• Recommendations (“Be sure to try the sweet potato fries or the fried green beans”, “Gotta come here folks!”)

Since online reviews can boost or hamper a restaurant brand, restaurant owners and managers must keep a close eye on how their establishments are being reviewed. Online reviews help them understand what their strengths are, what differentiates them from others, what issues need to be addressed before they impact their reputation, and what new trends are coming up.

Star ratings give a sense of how much customers like or dislike a place, but figuring out what exactly they like or dislike requires deeper analysis. With so many reviews and comments being generated continuously, a manual analysis is just not feasible or cost-effective. There is no simple automated solution either because language is rich and creative and there are myriad ways of expressing opinions, likes, and dislikes.  Here is where an AI-powered solution comes in handy.

Sentiment Analysis: the Missing Ingredient

Sentiment Analysis, also known as opinion mining, is about detecting likes, dislikes, emotions, and opinions and it’s often applied to social media, reviews, blogs, forum posts, chats, and similar sources.  Sentiment Analysis has many applications across many industries, but it’s especially well-suited for gathering insights and trends from online restaurant reviews.

Here is how:

1. Likes and Dislikes. Sentiment Analysis detects positive and negative sentiment. At a very basic level, it identifies positive and negative language and may associate those with co-occurring or high-frequency terms.  At an advanced level, through Entity- and Aspect-based Sentiment Analysis, it pinpoints the specific aspects that those positive and negative sentiments are about. For instance, patrons may love a restaurant’s large portions but complain about its noise level, difficult parking, or slow service. Being able to pinpoint what exactly people like and dislike is critical insight.
2. Intent. Advanced Sentiment Analysis detects language suggesting intent and sentiment-based actions like positive and negative recommendations, or worse, intent to never to come back or even boycott.  Detecting those intended actions can allow you to address the root causes of any perceived issues both for a specific establishment or restaurant brand as a whole and perhaps as importantly for the individual customer who had a bad experience.
3. Large Data Sample. Advanced Sentiment Analysis can scale to Big Data size, making it possible to process massive amounts of data in real time. Naturally, the larger the amount of data and the faster it can be processed, the more reliable, useful, and timely the insights will be.
4. Analytics. Advanced Sentiment Analysis normalizes the extracted information thus enabling data aggregation and quantification to provide the overall view from a large collection of content. A dashboard presents multiple views of the sentiment information through various types of interactive graphs and charts. Sentiment data can be sliced and diced as desired, for instance by positive and negative aspects (e.g., service, price, noise, parking, décor), and, if desired, the user can drill down to the source text for inspection and further analysis. Other useful charts show sentiment evolution over time through a sentiment timeline.
5. Competitive Analysis. The same type of analysis (e.g., likes, dislikes, intent) can be performed on competitors providing critical insight into a brand’s strengths and weaknesses in the marketplace.

To summarize, NetOwl’s advanced Sentiment Analysis can analyze restaurant reviews quantitatively and qualitatively to provide critical insight to thrive in a competitive restaurant industry.