Recommendation of Activity Sequences during Distributed Events by - PowerPoint PPT Presentation

Recommendation of Activity Sequences during Distributed Events by Diana Nurbakova Supervisors : Prof. Sylvie Calabretto, Prof. Jérôme Gensel, Dr. Léa Laporte Examiners : Prof. Patrice Bellot (reporter) Prof. Anne Boyer (reporter) Prof. Josiane Mothe Dr. Ilya Markov 13 December 2018

Motivation 2

Motivation 3

Motivation 4

Motivation 5

Motivation Very high density of events Average number of simultaneous events = 37 Max number of simultaneous events = 112 ▼ Need for Recommender System 6 Scenario 1: Overlapping events at Comic-Con w.r.t. 15 min long timeslots

Motivation Scenario 2: Program of activities on board of Disney Fantasy cruise 7

Motivation Desired Sequence of Activities Scenario 2: Program of activities on board of Disney Fantasy cruise 8

Motivation Desired Sequence of Activities Use of a Recommender System Scenario 2: Program of activities on board of Disney Fantasy cruise 9

Objectives & Research Questions Provide an integrated support for users to create a personalised itinerary of activities, in order to facilitate their decision making process during distributed events 10

Objectives & Research Questions Provide an integrated support for users to create a personalised itinerary of activities, in order to facilitate their decision making process during distributed events Conceptual Direction: Practical Direction: Analyse the field of recommendation of sequences of spatial items for a Provide an integrated framework to better understanding , conceptual address the defined problem definition and modelling of the field 11

Defense Itinerary Fantasy_db & DEvIR : datasets for RSSI You are here! and evaluation of Objectives &  5 min ANASTASIA Research Questions  10 min  13 min ANASTASIA : approach for solving RSSI RSSI :  12 min  3 min Recommendation of Conclusions & Sequences of Spatial Perspectives Items 12

Fantasy_db & DEvIR : datasets for RSSI and evaluation of Objectives &  5 min ANASTASIA Research Questions  10 min  13 min You are here! ANASTASIA : approach for solving RSSI RSSI : Recommendation  12 min  3 min of Sequences of Spatial Conclusions & Items Perspectives Recommendation of Sequences of Spatial Items (RSSI): From Recommender Systems to RSSI 13

Recommender Systems User Interaction log time Ordered list   of top- 𝑙 item_id  user_id items value ... Items  14  G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of- the-art and possible extensions. IEEE Trans. on Knowl. And Data Eng. , 17(6):734 – 749, June 2005

Recommender Systems    User     Interaction log    Users    time    ? Ordered list Items   of top- 𝑙 item_id  user_id items value ... Items  15  G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of- the-art and possible extensions. IEEE Trans. on Knowl. And Data Eng. , 17(6):734 – 749, June 2005

Recommender Systems    User     Interaction log    Users    time    ? Ordered list Items   of top- 𝑙 item_id  user_id items value ... Items Matrix completion problem (find missing values)  16  G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of- the-art and possible extensions. IEEE Trans. on Knowl. And Data Eng. , 17(6):734 – 749, June 2005

Recommender Systems: Spatial Items - Activity Activity on board of Disney Fantasy Identifier, 𝑗𝑒 0001 Name, 𝑜 Sailing Away Location, 𝑚 Deck Stage Start Time, 𝑢 𝑡 20.06.2015, 16h30 End Time, 𝑢 𝑓 20.06.2015, 17h15 Duration, 𝜀 45 min Categories, 𝒟 Characters , Fun for All Ages Description, d It’s time to go Sailing Away! Join Mickey and Minnie along with Tinker Bell and the rest of the gang as they welcome you aboard the Disney Fantasy. 17

Recommender Systems: Spatial Items - Activity Activity on board of Disney Fantasy Identifier, 𝑗𝑒 0001 Name, 𝑜 Sailing Away Location, 𝑚 Deck Stage Start Time, 𝑢 𝑡 20.06.2015, 16h30 End Time, 𝑢 𝑓 20.06.2015, 17h15 Duration, 𝜀 45 min Categories, 𝒟 Characters , Fun for All Ages Description, d It’s time to go Sailing Away! Join Mickey and Minnie along with Tinker Bell and the rest of the gang as they welcome you aboard the Disney Fantasy. 18

Recommender Systems: Spatial Items - Activity Activity on board of Disney Fantasy Identifier, 𝑗𝑒 0001 Name, 𝑜 Sailing Away Location, 𝑚 Deck Stage  Start Time, 𝑢 𝑡 20.06.2015, 16h30  End Time, 𝑢 𝑓 20.06.2015, 17h15  Duration, 𝜀 45 min Categories, 𝒟 Characters , Fun for All Ages Description, d It’s time to go Sailing Away! Join Mickey and Minnie along with Tinker Bell and the rest of the gang as they welcome you aboard the Disney Fantasy. 19

Recommender Systems: Spatial Items - Activity An activity 𝑏 represents an action of a certain duration that a user 𝑣 can attend or take at some geographically located point in a particular time window ( e.g., conference session, concert during the festival, activity/entertainment during the holidays). • Name, 𝑜 • Location, 𝑚 = (𝑦, 𝑧) • Time windows (start and end time), 𝑢 𝑡 , 𝑢 𝑓 • Duration (execution time), 𝜀 • Vector of categories, 𝑑 = (𝑑 1 , …, 𝑑 𝑙 ) • Description, 𝑒 Activity,  𝑏 = (id, 𝑜, 𝑚, 𝑢 𝑡 , 𝑢 𝑓 , 𝜀, 𝑑, 𝑒) 20

Recommender Systems: Spatial Items Single Items: Locations  21  Y. Zheng. Location-Based Social Networks: Users , pages 243 – 276. Springer New York, NY, 2011.

Recommender Systems: Spatial Items Single Items: Locations POIs  H. Yin, X. Zhou, Y. Shao, H. Wang, and S. Sadiq. Joint modeling of user check-in behaviors for point-of-interest recommendation. In Proc. of the 24th ACM CIKM ’15, pages 1631– 1640, 2015.  22  Z. Yu, H. Xu, Z. Yang, and B. Guo. Personalized travel package with multi-point-of-interest recommendation based on crowdsourced user footprints. IEEE Trans Hum Mach Syst. , 46(1):151 – 158, 2016.  I.R. Brilhante, J.A.F. de Macêdo, F.M. Nardini, R. Perego, and C. Renso. On planning sightseeing tours with tripbuilder. Inf. Process. Manage. , 51(2):1 – 15, 2015.

Recommender Systems: Spatial Items Single Items: 𝑢 2 𝑢 1 Locations POIs Events  X. Ji, Z Qiao, M. Xu, P. Zhang, C. Zhou, and L. Guo. Online event recommendation for event-based social networks. In Proceedings of the 24th WWW ’15 Companion, pages 45– 46, 2015.  23  K. Kaneiwa, M. Iwazume, and K. Fukuda. An upper ontology for event classifications and relations. In Proc. of the 20th Australian Joint Conference on Advances in Artificial Intelligence , AI’07, pages 394– 403, 2007.  E. Minkov, B. Charrow, J. Ledlie, S. Teller, and T. Jaakkola. Collaborative future eventrecommendation. In Proc. of the 19th ACM CIKM ’10, pages 819– 828, 2010.

Recommender Systems: Spatial Items Single Items: 𝑢 2 𝑢 1 Locations POIs Events/Activity 24

Recommender Systems: Spatial Items Single Items: 𝑢 2 𝑢 1 Locations POIs Events/Activity Sequential Items: t  Trajectory 25  Y. Zheng. Trajectory data mining: An overview. ACM Trans. Intell. Syst. Technol. , 6(3):29:1 – 29:41, 2015.

Recommender Systems: Spatial Items Single Items: 𝑢 2 𝑢 1 Locations POIs Events/Activity Sequential Items: 𝑢 2 t 𝑢 1 Trajectory 26 Itinerary (activity sequence)

Recommendation of Sequences of Activities during Distributed Events and Other RSSI POI Event Trip Activity Sequence [Yin 2015] [Minkov 2010, [Brilhante 2015, during Distributed Macedo 2015] Yu 2016, Events Zheng 2015]     List (sequence) recommendation     Unique Items     Unique Visit   Item Limited   Availability     Travel Time     Future oriented (lack of collaborative data)  I.R. Brilhante, J.A.F. de Macêdo, F.M. Nardini, R. Perego, and C. Renso. On planning sightseeing tours with  H. Yin, X. Zhou, Y. Shao, H. Wang, and S. Sadiq. Joint modeling of user check-in behaviors for point-of-interest tripbuilder. Inf. Process. Manage. , 51(2):1 – 15, 2015. recommendation. In Proc. of the 24th ACM CIKM ’15, pages 1631– 1640, 2015.   Z. Yu, H. Xu, Z. Yang, and B. Guo. Personalized travel package with multi-point-of-interest  E. Minkov, B. Charrow, J. Ledlie, S. Teller, and T. Jaakkola. Collaborative future eventrecommendation. In Proc. of recommendation based on crowdsourced user footprints. IEEE Trans Hum Mach Syst. , 46(1):151 – 158, 2016. the 19th ACM CIKM ’10, pages 819– 828, 2010. 27  Y. Zheng. Trajectory data mining: An overview. ACM Trans. Intell. Syst. Technol. , 6(3):29:1 – 29:41, 2015.  A.Q. Macedo, L.B. Marinho, and R.L.T. Santos. Context-aware event recommendation in event-based social networks. In Proc. of the 9th ACM RecSys ’15, pages 123– 130. 2015.