Scrape and Categorize Hotel Reviews
Project Title: Scrape and Categorize Hotel Reviews
Hi there, my team and I are looking to scrape data from TripAdvisor and Booking.com. We are looking to do this only for one hotel.
We would first like to scrape all the reviews and put them in an ordered manner in an excel sheet.
After this, we would like to split the reviews into customer segments: couples, families, groups of friends, solo travelers, business travelers. These are already the filters that one can use when browsing on TripAdvisor.
We would also like to split the customer reviews based on ‘topic’. These include: room, bathroom, breakfast, dinner, room service, spa, pool, bar, reception, location, noise, view, transport, other.
This is the part which is slightly more difficult, as it might require a word bank. For example, barely no customer will say ‘transport’ but might use the words ‘we couldn’t find a bus’, etc.
By the end of this, we would like to be able to sort reviews into the type of customer and topic. For example, 20% of the reviews are from the family segment. 10% of reviews by families wrote about ‘transport’.
I’m assuming the number of reviews won’t be too high, perhaps around 1000. The deadline is basically as soon as possible, ideally within next 5 days.
For similar work requirements feel free to email us on email@example.com.