Can social network be used for location-aware recommendation? Pasi Fränti, Karol Waga and Chaitanya Khurana P. Fränti, K. Waga, and C. Khurana Can social network be used for location-aware recommendation Int. Conf. on Web Information Systems & Technologies (WEBIST'15), 558 -565, 2015
Location-aware recommendation Location Input: • User • Location • Time • Keyword (optional) Recommendations: • Nearby services • Photos of other users Press here Results
Four aspects of relevance Example from practice 1. Content • Text description • Keywords (tags) 2. Time 4. User and his network • User profile • Social network User: Pasi • Recency of data • Season (not relevant in July) 3. Location • Distance to user Last skiing of winter Date: 4. 4. 2010 Location: N 62. 63 E 29. 86 Arppentie 5, Joensuu
Four aspects of relevance Example from practice 1. Content • Text description • Keywords (tags) 2. Time 4. User and his network • User profile • Social network User: Pasi • Recency of data • Season (not relevant in July) 3. Location • Distance to user Last skiing of winter Date: 4. 4. 2010 Location: N 62. 63 E 29. 86 Arppentie 5, Joensuu
Scoring of services Search History Location Rating Keyword seached frequently (SF) Distance between user and the place (SL) Rating by users in scale of 0 -5 (SR) Keyword searched nearby (SN) Keyword searched recently (SS) Normalizing to the scale [0, 1] Keyword searched by the user (SU) Total score: S = NH + 2 NL + NR + 1 History score: SH = SF + SN + SS + SU
Utilizing user network
Effectiveness of network • Social vs. information sharing • Buddy vs. stranger • Selected friends vs. ad hoc • On-line vs. offline network Popular networks: Facebook, Twitter, Google+, Instagram User activities: Likes, Comments, Retweet, favourite, rating. Activity stats in Facebook: 6 hrs/month, 2. 7 billion likes/day
Small world phenomenon FB friends: Average=261 463 261 68, 000 17 M Total reach: world 4. 6 B 229 55 298 88 298 193 580 142 • Entire world reachable in 6 steps (theory) • Experiment on Twitter users: 3. 43 steps
Distribution of information optimistic Friends sharing Reached 0. 01% 10% 1% 0. 1% 26 68 18 0 261 6, 786 17, 748 4, 698 Efficiency reduces Total reach: 29, 493
Distribution of information more realistic Friends sharing Reached 1% 0. 01% 0% 3 1 0 0 261 783 261 Efficiency reduces Total reach: 1, 305
Similarity of users Strength of link?
Methods for user similarity Friendship in Facebook • Existing link similar • Friend of a friend not considered Pages liked in Facebook • More matches more similar Places visited in Mopsi • Visits same places similar
Pages liked in Facebook Page similarity: Both like Hesburger Similar Alice Bob Category similarity: Both like Fast Food Restaurants Page name Page category
Page similarity = 14% Mikko (14) Radu (19) Philosophiæ Naturalis Principia Mathematica Computers and Intractability: A Guide to the Theory of NPCompleteness Nivan kylä Mopsi Impit Finland Kylpylähotelli Rauhalahti S+SSPR 2014 International Biographical Centre Joensuun Uimaseura Winter Swimming World Championships 2014 / Talviuinnin MM-kisat 2014 East Finland Graduate School in Computer Science and Engineering Joensuun Tiedepuisto Puhutun nykysuomen tutkimushanke Hello Jessie Epic Coders S+SSPR 2014 Team Four Star (Official) Pavo. Cons Graafinen suunnittelija - Pasi Seppänen Tripworks Oy Colegiul National Traian Impit Finland Mopsi East Finland Graduate School in Computer Science and Engineering Innovation Month Photo HD Boohoo Games Dr. James Grime Itä-Suomen yliopiston LUMA-keskus Polkujuoksu 13. 9. 2014 - Joensuu/Kontiolahti Senzo. Fit Odyssey 2014 Stomatolog Dr. Sabin Silviu Badea
Category similarity Mikko Book (2) Community (2) Attractions (1) Education (2) Travel (1) Community Organization (1) Company (1) Sports team (1) Amateur Sports team (1) Consulting (1) Business services (1) = 22% Radu Internet (1) Community organization (2) Tv show (1) Consulting (1) Media (1) Professional services (1) Education (4) Attractions (1) Website (1) Video game (1) Teacher (1) Non-profit organization (1) Sports event (1) Community (1) Health (1) Category Mikko (A) Radu (B) A B Community 2 1 1 Comm. Org. 1 2 1 Education 2 4 2 Consulting 1 1 1 Attractions 1 1 1 Total 6
Pre-processing categories Select first word Media/News/Publishing → Media Convert plural to singular Games/Toys → Games → Game TV channel → TV
Location similarity visit statistics 000 100 Places Visit frequencies 220 100 003 9 6 7 111 431 002
Similarity calculations Bhattacharyya distance 4 3 1 8 0. 44 0. 50 0. 14 0. 47 0. 26 2 2 0 4 0. 22 0. 33 0. 00 0. 27 0. 00 0 0 3 3 0. 00 0. 43 0. 00 1 1 1 3 0. 11 0. 17 0. 14 0. 15 0 0 2 2 0. 00 0. 28 0. 00 1 0 0 1 0. 11 0. 00 0 0 0. 00 9 6 7 0. 00 = 0. 88 -ln = 0. 13 0. 00 0. 41 0. 89
Collected data • 293 places (Mopsi services) • User activities until 31. 12. 2014 ‒ Photos taken ‒ Tracking started or ended 63. 44 N Joensuu sub-region 28. 65 E bounding box Municipalities: Joensuu Liperi Outokumpu Polvijärvi Kontiolahti Ilomantsi Juuka 62. 25 N 31. 58 E
Experimental results
Nine test persons Mopsi Facebook photos tracks friends pages Andrei 676 96 463 285 Julinka 3850 122 229 154 Mikko 190 84 55 14 Oili 6467 164 298 63 Pasi 9716 208 88 67 Radu 1417 122 298 19 716 85 193 16 Chait 63 22 580 195 Jukka 991 126 142 120 Rezaei
Survey questions Q 1: How similar you find the person is to you? Q 2: How useful you find his/her Mopsi photos? Context for Q 2: Does he recommend, via his/her Mopsi postings, useful and interesting places to visit in future.
User similarity Not friends in Facebook Influential users Everyone is like Radu
Expected usefulness • Mostly the same rankings (as with similarity) • Ranking of Pasi and Julinka improved • Expected vs. reality?
Most popular FB pages 8 Impit Finland S+SSPR 2014 ECSE 7 Mopsi 6 Joensuu Science Park 5 UEF - School of Computing Odyssey 2014 4 Sci. Fest Joensuu 3 Kaisa Mäkäräinen Jobs in Finland Joensuu - kaupunki idässä IMPDET-Le Polkujuoksu 13. 9. 2014 2 University of Eastern Finland Joensuu This is Finland Stieg Larsson Phd, Masters and Postdoc Intern. Scholarships Joensuun Jääkarhut - Joensuu Polar Bears Joensuun Susi University of Eastern Finland (UEF) Vatakka Fotoaurinko Scientific Writing Assistant (SWAN) Carlson Ilosaarirock Festival Suomen Luonto House Sauna Jenni Vartiainen Official Hello Jessie Itä-Suomen yliopiston LUMA-keskus ABBA Facebook for Every Phone Hannes Hynönen - Fanisivu Jukolan viesti 10 MILA The Herajärvenkierros Trail Kuopio Maraton
Page likes similarity Correlates with user evaluations: • Similarity: 0. 47 • Usefulness: 0. 17
Similarity Graph page similarities Jukka 0. 04 Oili 0. 08 0. 03 Pasi Chait 0. 03 0. 05 0. 07 0. 06 Mikko 0. 25 Radu 0. 16 0. 04 0. 14 Rezaei 0. 05 Andrei 0. 03 Julinka
Location data example
Location data example Correlates with user evaluations: • Similarity: 0. 28 • Usefulness: 0. 17
Conclusions • FB likes correlates to similarity • Location history has weaker correlation • Understanding of similarity interesting findings • Answer: YES, but question remains HOW. To be continued…
Скачать презентацию Can social network be used for location-aware
ddcc833f8e0218aecbfeb122bb0a7a34.ppt