At Triposo we make smart travel guides using algorithms. We crawl data from the web, apply some clever algorithms and automatically generate worldwide travel guides. Since this is the core of what we do, we obviously can't give away all our secrets, but this page will give you some more insight.
We start with data. We take all sorts of data and send our crawlers to fetch gigabytes of travel related content from different sources. We prefer to use open content that comes with little restrictions like World66, Wikivoyage, Wikipedia, Open Street Maps, TouristEye and Flickr. Where we find incorrect data, we try to find the source.
Once we have all the data, it is time to parse. From each source we try to extract all the information we can. We want to know everything about the city, village, country, restaurant, museum, or shop. To extract all that information automatically, we use a set of yaml files that define how the content is organized and identify data patterns.
After we've parsed everything, we end up with two big buckets of information, one about the places and one about the points of interest. Since we collect information from so many different sources, those places often pop up multiple times. Therefore, the next step is matching. After the matching phase, we have one complete record for each place.
Now it is time to determine what is most relevant to travelers. Traveler’s photos are a huge help in this phase. Using the exif data, we are able to determine where and when the photos were taken. If you combine this information with other data you can find out lots of interesting characteristics.
The density of travel-related words in articles describing a point of interest is another valuable source of information. We have a number of scripts analyzing the content that give us a very good indication of what an article is about, which snippets best describe it, how much people like it and how relevant it is to travelers.
Once our algorithms have determined which points of interest are most important, we start creating guides for countries and cities. We combine the descriptions from open sources with maps made using data from the Open Street Map project and there you go- a complete travel guide.
What we end up with is a complete overview of the the top attractions, things to do, and places to eat all ordered by relevance from a traveler’s perspective.