Products -> AI In-the-Box for Restaurant Reviews
AI In-the-Box for Restaurant Reviews consists of 128 Semantic Models. Each Semantic model was especially designed, built, tested, and re-tested on hundreds of thousands of restaurant reviews from multiple sources. All presented Semantic Models work with an unparalleled precision of 90-95%.
Below, you will find a high-level view of all semantic models designed for restaurant reviews.
In other words, what type of information do we garner from reviews.
Client loyalty & Recommendations
Will he come back? vs. not come back?
Will he recommend? vs. not recommend?
Overall good/satisfied. vs. Disappointed?
Is it good for: kids? couples? Special occasions? Meeting friends? Family meetings?
Restaurant’s General Opinions
Is the restaurant clean? dirty? renovated? outdated? smelly?
Need to wait for a table? Can’t book a table?
Need a reservation? Reservation problems?
Is it kids friendly? Got changing facilities, play area? Got kids menu?
Critical (dangerous to the brand) opinions
Hair in Food, Food poisoning, Bugs/Insects,
Restaurant was not as advertised,
Dirty restaurant, Service unpleasant/unprofessional
Food Taste & Quality Opinions
Food was tasty? Delicious? Mediocre? Poor? Bad? Tasteless?
Low-quality ingredients? Fresh? Poorly presented? Healthy food? Greasy? Unappetising? Perfectly cooked?
Opinions about specific dishes
Was a chicken tasty? Spaghetti was ok?
Grilled vegetables were crispy?
The dessert was fabulous?
Food Variety & Selection Opinions
Vegetarian menu? Vegan options? Gluten-free options?
Good wine/drinks selection? Good beer selection?
How about the menu? limited? rich?
Staff was friendly? Professional? Rude?
Waiting time was acceptable? Is delivery time quick?
Manager: friendly? professional? available?
Service was quick, slow? good?
Wifi - is it free? Is it fast?
Does parking have lots of spaces? limited? lack of parking?
Is suitable for a wheelchair? Is there good ventilation? AC?
Was it overpriced? Cheap, expensive? Was it worth them money?
Is there a service charge? Any additional fees? Bill problems?
Only cash payment?
Nice vibe? Cozy, relaxing atmosphere? Pleasant? Unpleasant vibe?
Not welcoming? The decor was nice? Interior outdated?
If there will be need, we can expand this list.
Search based on your individual preferences matched with opinions of similar people to you and data from reviews
What is important to you? Personalize your search
Our AI remember these parameters while reading millions of reviews and find you the best possible place
Our AI deeply analyzed 4.4 million reviews to match your personal needs and chose these places:
Meet the Alchemist Foodie. He has eaten everywhere and he has read all reviews in the world (and he remembers them all).
He is patient and he can spare a moment to find you new interesting places.
Instead of reading thousands of reviews individually, you can see a semantic summary and get a feeling for what is contained within them in 20 seconds. You can click for specific information and see extracted sentences from reviews.
Restaurantrestaurant in generaldecor nice 33 renovated 18 clean 15
Opinions & Recommendationsopinionoverall satisfied 34 will return 24 will recommend 9
Servicestafffriendly 23 competent 11 understaffed 9 unfriendly 4 uncompetent 2
Pricerestaurantexpensive 13 overpriced 9 adequate price 6
Foodtastedelicious 41 mediocre 5
Favourite dishesitalian pasta delicious 21 big portions 20
Addonswififree 13 problem 7 slow 4
The automatic summary made from reviews - after processed by our API (no additional NLP/NLU/ML or post-processing needed).
The first no-block title (Restaurant, Food etc.) is a Category from our API, blue blocks (Opinion, Staff etc.) are Aspects, green and red blocks (decor nice, renovated etc.) is the Feature and Polarity (Feature is text, Polarity is color).
See the live demo of semantic summary made from hotel reviews (powered by our technology).
First, you process all reviews of a given restaurant for a period of time (e.g. last 6 months) and extract important information with high accuracy. Then, it is easy to compare these results with other restaurants, and valuable patterns emerge.
Our AI deeply analyzed all 4489 of your reviews, compared with 1 200 000 reviews of similar businesses and extracted 11 Recommendations/Tips how you can improve your business:
Compare your parameters with similar businesses
Here, we focused on showing classified negative opinions critical to restaurant owners and presented on a brand reputation dashboard.
Slow service (5 mentions):
"We needed to wait for the order 30 mins!"
"Food is great, but very slow service..."
"waited with my friends 25 mins to order"
"great if you don't mind waiting"
"was hungry and waited almost an hour for the food"
By clicking on specific semantic category (here: Slow service) we get specific sentences/segments and "not the whole review" where people mentioned that the service was slow. We detect all the information that is correlated to slow service (e.g. "needed to wait", "if you don't mind waiting"), not just with keywords (e.g. slow, service). This is the advantage if you use Human-like Analysis (Semantic Analysis) instead of keywords.
You can see what reviews are about in 10 seconds. By clicking on specific information, you can go deeper (data zoom-in) and display actual sentences (not whole reviews).
Our AI deeply analyzed 3344 Reviews and organized them for you
(so you do not have to read them all)
|People was the most satisfied with:|
|Friendly, attentive Staff||
|Tasty, flavoursome Food||
|Cosy, relaxing Vibe||
|People complained about:|
|Restaurant dark, no light||
|Food not tasty||
|Problem with WiFi||
|show me more...|
By understanding a review better, you are able to provide deeper and easier-to-understand analysis for your clients.
Positive vs. Negative
Overall good/satisfied vs. Overall dissapointed
Will come back vs. Will not come back
Will recommend vs. Will not recommend
Language has color. Do not reduce it to black & white.
Information extracted by 128 Semantic Models is precise enough to create automatic text summary.
Natural Language Generation Summary from Reviews could look like this:
Our AI deeply analyzed all your reviews for the past 3 months, combined them with reviews of similar businesses and created this summary:
Almost everyone were satisfied with the service (in 87% of reviews) and friendly staff (72%), lot of them would come back (45 mentions) and will recommend this restaurant (33m.).
Reviews stats that restaurant is tiny (17 m.) but have romantic vibe (13 m.), which suits for a date (12 m.).
Unfortunately, customers complain about small portions (8 m.) and not enough spices in their food (5 m.).
Overall they think that it is expensive place (7 m.) but worth the money spend (13 m.).
|Semantic distribution summary out of text:|
|Would come back||
|Good for a date||
|Worth money spend||
Want to talk more about these solutions?
Example restaurant review:
Simplified output after processing by AI In-the-Box for Restaurant Reviews:
|1.||We are going to this place every sunday with my family||
good for family meeting +1
|2.||I love chicken masala there and i was not dissapointed, delicious||
food: chicken masala
|3.||We took pad thai as well and I must say it was not so tasty as other dishes||food: pad thai not tasty -1|
|4.||My wife and kids love there, they got a special kids menu, changing table and staff is friendly too||
kids menu available +1
changing facilities available +1
service staff friendly +1
|5.||As we were leaving the jazz band started to play and there was a lot of young people and you can feel the good vibe in the air||
live music nights +1
|6.||So, I recommend for a family, even for a friends meeting at evenings, do not recommend to a business meeting or romantic dinner)||
good for family +1
good for meeting friends +1
good for family +1
not good for business meeting -1
not good for romantic evening -1
We specialize in creating dedicated Natural Language Understanding engine for specific reviews. We focused in travel and prepared a set of products to process many different travel reviews (e.g. hotel, hostel, apartment, restaurant, airline reviews).
We stand by the statement that we detect more information than Watson or than any other Deep Learning solution and we are more accurate than Google in Travel Domain. We are also much more cost-effective. And we allow the processing of as much data as you want with no additional cost (0 cents / text).
This is possible because we created the next-generaion process of developing NLU systems in which we can build Semantic Models 10 x faster. It is designed from the ground up to process reviews, not proper english texts. It is the result of 12 years of experience in NLP/NLU and 8 years in processing reviews, and more than 50 big implementations (2007-2019) of NLU systems to process reviews and other user generated content.
We are passionate and proud of our technology and aim to provide the optimal technology for travel reviews. We will be happy to help you implement your brilliant ideas and discover what is possible.
|"Breakfast was tasty"||=>||Breakfast: positive|
|"Breakfast was huge"||=>||Breakfast: positive|
|"Breakfast was not free"||=>||Breakfast: negative|
|"Breakfast was very tasty but really small"||=>||Breakfast: neutral|
|"Breakfast was huge but you had to pay extra"||=>||Breakfast: neutral|
|"Breakfast was tasty"||=>||Breakfast: tasty|
|"Breakfast was huge"||=>||Breakfast: big portions|
|"Breakfast was not free"||=>||Breakfast: free|
|"Breakfast was very tasty but really small"||=>||Breakfast: tasty | small portions|
|"Breakfast was huge but you had to pay extra"||=>||Breakfast: big portions | not free|
Language has colors. Do not reduce it to Black & White.
Technological differences (compared to other NLP/NLU solutions):
The semantic model is the newest approach to an information extraction models where boundaries of those models are not determined by the structure of a language (or grammar, or used words), but the type of information you are detecting. It does not matter how the user writes an opinion about a specific object, e.g. “breakfast was a joke”, “Muffin and cold coffee is not a breakfast”, “Breakfast wasn’t included as written”, our semantic model still detects it and provides structured-data. With "breakfast" example, it is relatively easy to provide a shallow analysis (e.g. Sentiment Analysis) with the current NLP techniques. If you are looking for more sophisticated information (e.g. is it safe?, is it handicap friendly?, will someone come back?, Is it sustainable? Is it pet-friendly?) the situation gets more complicated. Current techniques provide a part of this information and their accuracy relies on the keywords used in reviews. Users are very creative in the reviews and they are not using a keyword approach. Let’s take one example. If we want to answer the question “is it safe?”, you need to capture a lot of information from reviews without common keywords safe/dangerous. In practice they write this in tens or hundreds of ways: e.g. “there was a lot of drunken people outside”, “I did not feel good because of the neighbors”, “someone yelled in the night and the front desk lady did nothing”. We believe, that if the human can understand what is written in the review, then technology should detect it as well. That is why we call them Semantic Models, not information extraction models.
Our UnicornNLP Semantic Environment is a place where we design and precisely craft all the semantic models. It is a perfect combination of human and computer intelligence. It is the secret sauce of our technology and it allows us to deliver the best technology in the world for reviews. Statistical algorithms provide the data based on the processing of hundreds of thousands of reviews, but the humans are making all the crucial decisions. Given the pace of AI development, this is significant advantage in information extraction (in NLP/NLU) and it will be appropriate for the next decade. Think about our environment as a way of creating tens of thousands of very precise, hand-crafted semantic rules but with an AI as an assistant that is generating new ideas. These ideas are provided by an AI assistant based on constant simulations on real data and statistical tools.
We designed a semantic programming language (QL4Reviews) to extract information from reviews. With this programming language, you build semantic models 10 times faster than in other current technologies. Every Semantic Model is programmed in QL4Reviews and consist of 50-2000 lines of semantic code. Heavily optimized engine allow to process through 124 Semantic Models on 1 low-cpu Amazon AWS instance - 1 million reviews a day. Speed of the core engine was very important for us from the beginning.
Our technology is designed from the ground up to process reviews, not proper-grammar texts. It can process also machine-translated reviews/texts (via Google Translate or Microsoft Translate). This approach provides almost as good results as processing English reviews but we do not have to rewrite deep semantic models into other languages. It is much easier to maintain and scale (because there is only 1 engine).
Read more & See demo: Processing machine-translated non-English Travel Reviews
This is not just another NLP API/Tool. We redesigned every layer of technology and we wanted to address the biggest challenge in the NLP/NLU industry. We wanted to change the way you use and think about Natural Language Understanding API. In our opinion, if you are using NLP API, you should not get your hands dirty and spend inordinate time thinking how to best implement this API into your application. We wanted to hide all the NLP complexity inside the system and provide you ready-to-use data. We believe that NLP API should be simple and easy to use without linguistic, machine learning or other expertise. You do not need to spend weeks to improve the accuracy of "domain-indepentent" NLP API, to adjust to Your domain or to make decisions about complex output parameters. Getting output parameters like confidency (e.g. 0.7852) or polarity (e.g. 0.4352) or keywords detected (e.g. friendly, 0.6786; dissapointed, -0.7564) gives every developer problems and frankly they are not standard or predictable. They are rather a consequence of used technology inside, and putting these parameters for the output in our opinion is the way to leave configuration and responsibilty for decision-making to You. We believe in human-like output where a human can understand what this API detected. We believe that we have developed excellent API for specific domains, so you can get tailored results and focus on your business. We position ourselfes as a read-to-use technology, not a standard API that is a tool that you need to configure and train to your data.
If you want to buy a Product, receive more info about the On-Premise version (AI In-the-Box) and Plans&Pricing
or want to discuss what is possible
If you want to test it or see how it works on your data, send us a dataset
(we do not collect your data)
You can also start with the SaaS version - pay per text (hosted via rapidAPI & Amazon AWS)
before you get the On-Premise version with 0 cents / text!