The project “Advanced Tourism Planning System – Advanced Tourism Planning System (ATLAS)” which is implemented by the program ‘’Cooperation 2011’’-
Producer and Research Partnerships in Focused Research and Technology Sectors is a partnership between two research organizations: Aristotle University of Thessaloniki, Laboratory of Artificial Intelligence and Information Analysis, Department of Informatics and “ATHENA” – Research Center for Innovation in Information Technology of Communications and the companies LINK TECHNOLOGIES SA, 3PI INFORMATIONS SYSTEMS SA. Tourism is a vital economic sector for Greece contributing significantly to country’s gross domestic product. To increase the value of the country’s touristic product against competitors, not only infrastructure, marketing, and e-commerce services should be ameliorated, but advanced and unique information services should also be deployed, which will take into account contextual information, such as personal preferences, time-dimension, and geographical location. Clearly, planning a visit is not limited to searching the web through Google or reading more about the venue in Wikipedia. This could be considered as the equivalent of browsing an encyclopedia or consulting a tourist guide. The outcome of such a retrieval task exhibits low precision, because visitor preferences, time-updated information about the events taking place in the venue during the visit, are totally ignored. Such missing information can easily be found in social networking websites (e.g., Facebook, Twitter) and multimedia content (image, video, music) sharing websites (e.g., Flickr, Panoramio, Youtube, Last.fm), where tags disclose users’ behaviour, geo-context, and ratings matched to visitor ones. Tags are textual labels, typically a short list of keywords, associated to photos, web page, blog, which have been proven a powerful and useful feature in Web 2 (Flickr, Panoramio, Youtube, etc.). Unlike category, tags offer unstructured knowledge with no a- priori semantics. Geographical information, such as geo-tag, map, Google street view data, GPS information, user location reveals the relative position to a specific object. For example, the availability of geotagged photos allows a use to access photos relevant to his/her current location. There is a dearth of methods for discovering and linking such spatially and socially related photos. Each geotagged photo (i.e.geo-referenced image) has in addition an associated location and time.The project ATLAS utilizes images whose exact location was automatically captured by the camera or a location-aware device or alternatively specified by the user through the functionalities and tools offered by Flickr, Panoramio, Youtube. Exploitation of visitor preferences and geographical information will leverage cross‐media/multimedia information retrieval and recommendation for e‐tourism. This is the first advanced functionality ATLAS offers. The ATLAS project seeks ways to improve online tourism services on the basis of the following observations: The provision and retrieval of tourism information is not limited to text and photographs. The uniqueness of ATLAS approach compared to other similar initiatives lies in its completeness. The completeness of its approach makes the solutions proposed by ATLAS interesting for a broad scope of users including (i) tourism industry, (ii) the ordinary end-users, and (iii) social scientists (e.g. anthropologists).