To present you what this technology can do we are using the case of the Semantic Analysis for Hotel Review. For solutions in different domain (e.g. restaurants) go to Products site and select specific product (e.g. Semantic Analysis for Restaurant Reviews). You can also contact us to discuss a specific solution.
Click to go to the specific solution, or scroll down the page and see in how many areas this technology could be applied.
1.1. Automatic Conversion of Reviews into Recommendations/Tickets/Tips (for Business Owners)
1.2. Human-like (Semantic) classification of reviews (for Business Owners)
1.3. Human-like (Semantic) comparison of 2 hotels (for Business Owners)
2.1. Travel Hotel/Accommodation Search personalization (for Travelers)
2.2. Travel chatbot fueled by reviews - Automatic learning of facts and opinions from reviews and using it in conversation (the next-generation of Travel Chatbots)
2.3. Human-like (Semantic) summary of reviews (for Travelers)
3.1. Semantic Distribution and TagCloud out of 1000+ reviews (for travelers&Business Owners)
3.2. Automatic Cognitive Report Generation from Reviews (for Travelers&Business Owners)
If you have other ideas and you would like to discover is it possible, Contact us.
First, you process all reviews of a given hotel and extract important information with high accuracy. Then, it is easy to compare these results with other hotels, and valuable patterns emerge.
We analyzed all 4423 of your reviews, compared with 450 000 reviews of similar businesses and extracted 14 Recommendations/Tips how you can improve your business:
Compare your parameters with similar businesses
Here, we focused on showing classified negative opinions critical to hotel owners and grouped them semantically.
By clicking on a specific semantic category (here: Noisy rooms) we get specific sentences/segments and "not the whole review" where people mentioned noisy rooms. We detect all the information that is semanticaly correlated to noisy rooms (e.g. "cleaning service did not their job"; "it was far from clean"), not just related keywords (e.g. dirty, messy). This is the advantage if you use Cognitive Learning instead of keywords/machine learning models.
Below is a simple comparison made only using 200 reviews and limited categories/areas. You have 149 Semantic Models at your disposal which can be used to make comparisons in general or in very specific areas.
Marriott, San Francisco (8.5 on booking.com)vs. Hilton, San Francisco (7.8 on booking.com) |
|
Cleanliness comparison: |
|
room
clean 25
dirty 1 bathroom clean 1 dirty 10 cleaning service good 4 poor 4 bed dirty 1 Positive: 30, Negative: 16 |
room
clean 27
dirty 14 bathroom clean 1 dirty 7 cleaning service good 5 poor 16 bed dirty 6 Positive: 33, Negative: 43 |
Service comparison: |
|
staff
helpful, friendly 94
unhelpful, unfriendly 9 check-in fast 8 slow 1 Positive: 102, Negative: 10 |
staff
helpful, friendly 57
unhelpful, unfriendly 35 check-in fast 22 slow 8 Positive: 79, Negative: 43 |
Addons comparison (comparing only negative opinions): |
|
wi-fi
not free 20
problem 2
slow 1 parking not free 12 small 1 Negative: 37 |
wi-fi
not free 9
problem 5
slow 1 parking not free 16 Negative: 31 |
Clients Opinion comparison: |
|
opinion
overall good, satisfied 6
will return 4
will recommend 2
overall disappointed 2
will not return 3 Positive: 12, Negative: 5 |
opinion
overall good, satisfied 4
will return 5
will recommend 4
overall disappointed 14
will not return 7
not recommend 3
Positive: 13, Negative: 24 |
Marriott, San Francisco wins (Positive: 144, Negative: 68)
over Hilton, San Francisco (Positive: 105, Negative: 141).
On Booking.com Marriott also got a higher rate (8.5) compared to Hilton rate (7.5).
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
We remember these parameters while reading millions of reviews and find you the best possible place
We analyzed 3 million reviews from Berlin to match your personal needs:
Meet the Alchemist Traveler. He has been 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 plan your perfect vacation.
Example 1:
Example 2:
Example 3:
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.
Hotel
hoteloutdated 23 smelly 22 clean 15 not as advertised 4Room
roomclean 34 spacious 22 well equiped 15 sth broken 4Service
staffhelpful, friendly 23 unhelpful, unfriendly 15 check-in slow 12Food
breakfastrich, plenty options 13 not free as promised 9 great 6Price
hoteloverpriced 23 money waste 15 adequate price 4Location
close tohighway 7 city center 5 public transportation 4Addons
wififree 11 problem 9 slow 7Other
deal breakerssth stolen 4bugs 2The automatic summary made from reviews - after processing by Semantic Analysis for Hotel Reviews (no additional NLP/NLU/ML or post-processing needed).
The first no-block title (Hotel, Price etc.) is a Category from our API, blue blocks (Bathroom, Payment etc.) are Aspects, green and red blocks (outdated, well equipped 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).
All displayed results make sense. By clicking on specific information, you can display actual sentences (not whole reviews).
We analyzed 4765 Reviews and get Top Strengths & Weaknesses of this place
(so you do not have to read hundreds of reviews)
Top 5 Strengths (People were the most satisfied with): | |
Rich Breakfast | |
Clean Room | |
Hotel Renovated | |
Well-Equiped Room | |
Fast Check-in | |
Top 3 Weaknesses (People complained about): | |
Pool Closed | |
Problem with Refund | |
Problem with WiFi | |
show me more... |
Client loyalty analysis
Overall good/satisfied vs. Overall dissapointed
Will come back vs. Will not come back
Will recommend vs. Will not recommend
Information extracted by 149 Semantic Models is precise enough to create automatic text summary.
Natural Language Generation Summary from Reviews could look like this:
We analyzed all your reviews for the past 3 months, combined them with reviews of similar businesses and automatically created this summary:
Most of people (88%) was satisfied with their stay, a lot of people (47 mentions) wrote that they would come back and will recommend this apartment (24 m.).
Reviewers state that rooms in this apartment are clean (34 mentions) and spacious (22 m.) and well-equipped (15 m.). Unfortunately, reviewers also stated that the apartment was outdated (23 m.) and smelly (22 m.). The majority found the staff helpful and friendly (23 m.) but some stated that they were unprofessional (19 m.) and the check-in process (12 m.) was slow.
There were also some issues with the Pool (23m.) and the Gym (15m.)
Generally, people say it is a good value for money (42m.).
Semantic distribution summary out of text: | |
Overall good/satisfied | |
Would come back | |
Will Recommend | |
Clean Rooms | |
Spacious Rooms | |
Well-equipped Rooms | |
Outdated Hotel | |
Smelly Rooms | |
Friendly Staff | |
Unprofessional Staff | |
Slow Check-in | |
Issues with Pool | |
Issues with Gym | |
Good value for money |
If you would like to talk more about these solutions, or discover what is possible