Unicorn NLP

Deep AI for Travel Reviews

Unicorn NLP

Deep AI for Travel Reviews

Solutions in Travel
(what AI In-the-Box for Travel Reviews can do)

To present you what this technology can do we are using the case of the AI In-the-Box for Hotel Review. For solutions in different domain (e.g. restaurants) go to Products site and select specific product (e.g. AI In-the-Box for Restaurant Reviews).


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/Hostel/Apartment Search personalization (for Travelers)
2.2. Travel chatbot en(c)hancement - Automatic learning of facts and opinions from reviews (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. Human-Like Client Loyalty Analysis (1-dimension deeper than Sentiment Analysis).
3.3. AI-powered Automatic Review Report Generation (for travelers&business owners)


1. AI-powered new analytical dashboards (for business owners)

1.1. Automatic Conversion of Reviews into Recommendations/Tips (for Business Owners)

First, you process all reviews of a given apartment and extract important information with high accuracy. Then, it is easy to compare these results with other apartments, and valuable patterns emerge.


Our AI deeply 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:


  • Consider making bigger portions of the breakfast (7% complained in reviews - compared to 4.5% average) - read more and see reviews...
  • Repair the elevator (5% complained) and keep the pool open for a whole year (9% complained) - read more and see reviews...
  • Consider improving the speed of the WiFi (11% complained) and make it work in the room, not only in the lobby (5% complained) - read more...
  • Talk with your Manager so he could be more available for your clients (8% complained) - read more and see reviews...
  • Train your staff to be more friendly (12% complained) and more professional (4% complained) - read more and see reviews...
Extract more Recommendations from Reviews...

Compare your parameters with similar businesses

1.2. Human-like (Semantic) classification of reviews (for Business Owners)

Here, we focused on showing classified negative opinions critical to hotel owners and presented on a brand reputation dashboard.


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 correlated to noisy rooms (e.g. cleaner is banging around), not just with keywords (e.g. noisy, loud). This is the advantage if you use Human-like Analysis (Semantic Analysis) instead of keywords.

1.3. Human-like (Semantic) comparison of 2 hotels (for Business Owners)

Below is a simple comparison made only using 200 reviews and limited categories/areas. You have 124 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).




2. AI powered travel search & discovery & chatbots (for travelers)

2.1. Travel Hotel/Accommodation Search personalization (for Travelers)

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

  • Friendly, Professional Staff, frequent Cleaning Service
  • Big, Well-equipped Gym
  • Fast WiFi, everywhere
  • Free, big, tasty Breakfast
  • Handicap accessible & working Elevator
  • No hidden fees, No problem with Refunds
  • Nicely decorated place, clean, updated rooms
  • Clean, Well-equipped Bathroom, no shower problems
  • Fast Check-in, professional front-desk
  • more...
  • Recommended for (based on reviews)
    Solo, With children, Business trip, Romantic trip, Anniversary, Wedding, Quiet stay, Pet friendly
  • Close to (based on reviews)
    Restaurants, Local Atractions, Airport, Highway,
    Public Transport., Shopping, City center, Nature

Our AI deeply analyzed 3 million reviews from Berlin to match your personal needs:

2.2. Travel chatbot fueled by reviews - Automatic learning of information and users opinions from reviews and using it in conversation.

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:

Where are you going?
Barcelona
Great, please describe what it is important to You or select by tapping on the screen
working free wifi, working pool, pet friendly and no smelly rooms
Good choice! I have just analyzed 3 millions (wow! right?) reviews against your needs and I found 17 places.
...

Example 2:

Where are you going?
Barcelona
What is important to You?
I don’t like dogs, children, need elevator
Got it! Something more?
no hidden fees and deposits
I have just analyzed 3 millions (wow! right?) reviews against your needs and I found 12 places.
...

Example 3:

...
You selected Hotel A in Barcelona, do you have some questions about it?
oh yes, very important, is it handicap friendly for real?
Yes, 24 guests stated in reviews that it is handicap friendly, do you want to see specific sentences from reviews of that guests?
yes please
“i was satisfied that elevator was working properly because I was with my eldery aunt”, “staff of the hotel take very good care of my old papa”, bathroom was handicap accessible!”
great, book it!

2.3. Human-like (Semantic) summary of reviews (for Travelers)

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 4
opinionoverall disappointed 34 will not return 22 will recommend 9

Room

roomclean 34 spacious 22 well equiped 15 sth broken 4
bathroomwell equipped 23 shower problem 19 clean 15 outdated 13 small 8

Service

staffhelpful, friendly 23 unhelpful, unfriendly 15 check-in slow 12
restaurant servicepoor, slow 8
managerunhelpful, ineffective 8
valet servicebad, slow 23

Food

breakfastrich, plenty options 13 not free as promised 9 great 6
pricefood overpriced 7

Price

hoteloverpriced 23 money waste 15 adequate price 4
paymentbill problem 8 additional fees 5 refound problem 3

Location

close tohighway 7 city center 5 public transportation 4
neighborhood not safe 14

Addons

wififree 11 problem 9 slow 7
tvbad, poor channels 13
parkingsmall 19 not free 17
poolclosed 8
handicapnot accessible 9

Other

deal breakerssth stolen 4bugs 2

The automatic summary made from reviews - after processing by AI In-the-Box 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).

3. Other solutions in Travel

3.1. Semantic Distribution and TagCloud out of 1000+ reviews (for travelers&business owners)

All displayed results make sense. By clicking on specific information, you can display actual sentences (not whole reviews).


Our AI deeply analyzed 4765 Reviews and organized them for you
(so you do not have to read them all)

People were the most satisfied with:
Rich Breakfast
16%
Clean Room
14%
Hotel Renovated
12%
Well-Equiped Room
11%
Fast Check-in
9%
People complained about:
Pool Closed
7%
Problem with Refund
5%
Problem with WiFi
4%
show me more...

3.2. Human-Like Client Loyalty Analysis (1-dimension deeper than Sentiment Analysis).

By understanding a review better, you are able to provide deeper and easier-to-understand analysis for your clients.


1. Sentiment Analysis (positive vs. negative, Black&White approach)

Positive vs. Negative

80%
20%

2. Human-like Analysis (semantic, COLOR approach)

Overall good/satisfied vs. Overall dissapointed

92%
8%

Will come back vs. Will not come back

74%
26%

Will recommend vs. Will not recommend

85%
15%

Language has color. Do not reduce it to black & white.

3.3. AI-powered Automatic Review Report Generation (for travelers&business owners)

Information extracted by 124 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:


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
88%
Would come back
47 mentions
Will Recommend
24 mentions
Clean Rooms
34 mentions
Spacious Rooms
22 mentions
Well-equipped Rooms
15 mentions
Outdated Hotel
23 mentions
Smelly Rooms
22 mentions
Friendly Staff
23 mentions
Unprofessional Staff
19 mentions
Slow Check-in
12 mentions
Issues with Pool
23 mentions
Issues with Gym
15 mentions
Good value for money
42 mentions

Want to talk more about these solutions?

Contact Us

Or see our products especially designed for travel reviews.


See all products for travel domain