TripBuilder - Talk @ databeersTUS, Florence
•Descargar como PPTX, PDF•
0 recomendaciones•160 vistas
Talk at databeersTUS (Florence, October 20, 2016) presenting the article: "On Planning Sightseeing Tours with TripBuilder" by Igo Ramalho Brilhante, Jose Antonio Macedo, Franco Maria Nardini, Raffaele Perego, Chiara Renso. Information Processing & Management (Elsevier). 2014.
Recomendados
Recomendados
Más contenido relacionado
Destacado
Destacado (17)
Último
Último (20)
TripBuilder - Talk @ databeersTUS, Florence
- 1. On Planning Sightseeing Tours with TripBuilder Igo Brilhante1, Jose Antonio Macedo1 Franco Maria Nardini2, Raffaele Perego2, Chiara Renso2 1 Federal University of Ceará, Fortaleza, Brasil 2 HPC Lab, ISTI-CNR, Pisa, Italy
- 2. California Academy of Sciences Aquarium of the Bay Alcatraz de Young Museum Golden Gate Bridge Golden Gate Park San Francisco Museum of Modern Art Trip Planning What should I visit in San Francisco? Constraints: • Time: 2 days; • My preferences. How do other tourists visit such places? How many of these “trajectories” can I enjoy? TripBuilder: an unsupervised framework for trip planning. 4 h 4 h 8 h
- 3. Flickr • Vast amount of rich data – 586 M public Photos uploaded in 2013 – (Geo-)Tags, Titles, likes, Descriptions, Comments, Social profiles • Easy to crawl • Existing large public crawls: – CoPhIR: http://cophir.isti.cnr.it/ • Bulk uploading very common
- 5. (credits to David Crandall et al., Cornell University)
- 6. Trajectories from Flickr & Wikipedia
- 7. The TripCover Problem • Given: – A set of popular trajectories crossing a set of PoIs and their time cost – The relevance of the trajectories w.r.t. the category set – The Time Budget and Preferences of a user – A measure of PoI-User interest • Find: – the subset of trajectories that maximizes user interest and fits in the time budget
- 8. TrajSP: Joining Trajectories • A TripCover solution is a set of trajectories fitting user interest and time budget – Local search heuristics based on 2-opt and 3-opt for connecting the solution in a single sightseeing tour
- 9. TripBuilder: Overview City Budget Categories Personalization Tour TripBuilder HDFS HDFS HDFS Wikipedia PoI Discovery Photo Discovery Users' Photos Poi Visiting Time Estimation Trajectories Creation Stream Layer Batch Layer Distributed Data Storage City Bounding Box Apache Storm (+ Kafka & Cassandra) Apache Spark
- 10. http://tripbuilder.isti.cnr.it Coming soon on iTunes Store and Google Play! BEST DEMO ECIR 2014
- 11. Thanks! Questions? Franco Maria Nardini francomaria.nardini@isti.cnr.it http://hpc.isti.cnr.it/~nardini/ http://tripbuilder.isti.cnr.it/about Print-outs of all the images uploaded to Flickr in a day (Installation by Erik Kessels, Amsterdam)
Notas del editor
- At last but not at least we have photo sharing sites such as Flickr. Many papers showed that Flickr is very useful for tourism analysis. Main reasons: High, constantly increasing fraction of geotagged photos Rich social network with useful information Easy to crawl Bulk uploading very common (movement information!!) Tourism bias
- The interesting thing is that Flickr data have a bias…. Tourism bias: Picks occurring in correspondance with summer (and winter) holidays are a quite strong signal of the relevance for tourism-oriented analysis
- Tourism bias also on coverage We must be however aware even of the demographics bias inherent in such kind of data (digital native)