A Novelty-Seeking based Dining Recommender System

    WWW, pp. 1362-1372, 2015.

    Cited by: 33|Bibtex|Views14|Links
    EI
    Keywords:
    dining behaviordining recommender systemHigh Order Singular Value Decompositionrecommender systemPoint of InterestMore(6+)
    Wei bo:
    This paper proposes a dining recommender system termed novelty-seeking based dining recommender system, which gives associated recommendation strategies according to different novelty-seeking statuses

    Abstract:

    The rapid growth of location-based services provide the potential to understand people's mobility pattern at an unprecedented level, which can also enable food-service industry to accurately predict consumer's dining behavior. In this paper, by leveraging users' historical dining pattern, socio-demographic characteristics and restaurants'...More

    Code:

    Data:

    0
    Introduction
    • Dining out has become one of the most distinctive aesthetic features of urban life [27].
    • More than 35% location visit is made at new places each day even after half a year according to the reported results in [6]
    • This neophilia characteristic is extremely outstanding in dining behavior, e.g., [3] discovered that an appropriate degree of novelty-seeking as well as attendant risk could be essential ingredients in entertainment and excitement for users’ dining out motivation.
    • This neophilia characteristic is extremely outstanding in dining behavior, e.g., [3] discovered that an appropriate degree of novelty-seeking as well as attendant risk could be essential ingredients in entertainment and excitement for users’ dining out motivation. [17] stated that the physiological and psychological motivators which cannot be fulfilled in a user’s normal daily life are likely to be satisfied by a sense of adventure, uniqueness of the setting, experience of different cultures and the opportunity of sampling new foods
    Highlights
    • Dining out has become one of the most distinctive aesthetic features of urban life [27]
    • We present a framework, termed novelty-seeking based dining recommender system (NDRS), to generate the top-K restaurants for the dining
    • To infer a user’s noveltyseeking status, we present a Conditional Random Field (CRF) to model the sequential dependency of novelty-seeking statuses in consideration of spatial, temporal and historical factors that would influence the novelty-seeking decision
    • To infer the novelty-seeking status s of dining, we propose a conditional random field (CRF) with additional constraints method which incorporates a Conditional Random Field model with priori knowledge as constraints
    • This paper proposes a dining recommender system termed novelty-seeking based dining recommender system, which gives associated recommendation strategies according to different novelty-seeking statuses
    • This research sheds new light on other recommender systems such as Point of Interest and music recommendation, which can be used in more application scenarios
    Methods
    • The authors first describe and analyze the data the authors collected from two specific websites.
    • The evaluation method of novel recommendation is as follows: 1) For each city, the authors collect all the users who reside in this city and use their training check-ins to learn a model and obtain a user’s evaluation result on her novel check-ins in the testing data.
    • 2) The final result is the average value of the results from all users
    • Note that in this part, the testing data includes both novel and regular check-ins.
    Results
    • More than 35% location visit is made at new places each day even after half a year according to the reported results in [6].
    Conclusion
    • This paper proposes a dining recommender system termed NDRS, which gives associated recommendation strategies according to different novelty-seeking statuses.
    • The authors first design a CRF with constraints to infer novelty-seeking status.
    • A context-aware collaborative filtering method and a HMM with temporal regularity method are proposed for novel and regular restaurant recommendation, respectively.
    • The extensive experiments the authors have conducted validated the effectiveness of the dining recommender system.
    • This research sheds new light on other recommender systems such as POI and music recommendation, which can be used in more application scenarios
    Summary
    • Introduction:

      Dining out has become one of the most distinctive aesthetic features of urban life [27].
    • More than 35% location visit is made at new places each day even after half a year according to the reported results in [6]
    • This neophilia characteristic is extremely outstanding in dining behavior, e.g., [3] discovered that an appropriate degree of novelty-seeking as well as attendant risk could be essential ingredients in entertainment and excitement for users’ dining out motivation.
    • This neophilia characteristic is extremely outstanding in dining behavior, e.g., [3] discovered that an appropriate degree of novelty-seeking as well as attendant risk could be essential ingredients in entertainment and excitement for users’ dining out motivation. [17] stated that the physiological and psychological motivators which cannot be fulfilled in a user’s normal daily life are likely to be satisfied by a sense of adventure, uniqueness of the setting, experience of different cultures and the opportunity of sampling new foods
    • Methods:

      The authors first describe and analyze the data the authors collected from two specific websites.
    • The evaluation method of novel recommendation is as follows: 1) For each city, the authors collect all the users who reside in this city and use their training check-ins to learn a model and obtain a user’s evaluation result on her novel check-ins in the testing data.
    • 2) The final result is the average value of the results from all users
    • Note that in this part, the testing data includes both novel and regular check-ins.
    • Results:

      More than 35% location visit is made at new places each day even after half a year according to the reported results in [6].
    • Conclusion:

      This paper proposes a dining recommender system termed NDRS, which gives associated recommendation strategies according to different novelty-seeking statuses.
    • The authors first design a CRF with constraints to infer novelty-seeking status.
    • A context-aware collaborative filtering method and a HMM with temporal regularity method are proposed for novel and regular restaurant recommendation, respectively.
    • The extensive experiments the authors have conducted validated the effectiveness of the dining recommender system.
    • This research sheds new light on other recommender systems such as POI and music recommendation, which can be used in more application scenarios
    Tables
    • Table1: Summarization of collected dataset for different cities (partially presented due to page limit)
    • Table2: The results of novelty-seeking inference
    • Table3: The results nDCG@10 of recommending regular restaurants
    Download tables as Excel
    Related work
    • 8.1 Location Recommendation

      In recent years, with the rapid accumulation of spatial-temporal records in the check-in data and the prevalence of various interesting real-world applications [40], the location recommendation problem has received much attention. Ye et al [38] exploited the social and geographical characteristics of users and location/places to generate the next location recommendation. Zheng et al [47] used GPS data and users’ comments at various locations to discover interesting locations and possible activities that can be performed for recommendation. Cheng et al [4] first fused matrix factorization with geographical and social influence for POI recommendation.

      Compared to previous works which mainly focus on regular mobility patterns, our work primarily aims at proposing a framework based on novelty-seeking status to predict whether a user will visit novel restaurants or regular restaurants.

      8.2 Novelty-Seeking in Dining Behavior

      Novelty seeking is also termed sensation seeking or neophilia. It has long been studied in psychology, consumer behavior and health science [11, 14, 23]. Acker and Mcreynolds [1] mentioned that novelty-seeking appears to be that through internal drive and external motivating force, the individual is then motivated to seek out novel information. There are two aspects to novelty-seeking that are likely to be correlated. The first aspect is seeking new and potentially discrepant information, which is emphasized by Fiske and Maddi [12]. The second aspect is the extent to which individuals would like to vary their choices among familiar contexts [13].
    Reference
    • M. Acker and P. McReynolds. The" need for novelty": A comparison of six instruments. The Psychological Record, 1967.
      Google ScholarLocate open access versionFindings
    • G. Adomavicius, R. Sankaranarayanan, S. Sen, and A. Tuzhilin. Incorporating contextual information in recommender systems using a multidimensional approach. ACM Transactions on Information Systems (TOIS), 23(1):103–145, 2005.
      Google ScholarLocate open access versionFindings
    • T. D. Andersson and L. Mossberg. The dining experience: do restaurants satisfy customer needs? Food Service Technology, 4(4):171–177, 2004.
      Google ScholarLocate open access versionFindings
    • C. Cheng, H. Yang, I. King, and M. R. Lyu. Fused matrix factorization with geographical and social influence in locationbased social networks. In AAAI, volume 12, page 1, 2012.
      Google ScholarLocate open access versionFindings
    • C. Cheng, H. Yang, M. R. Lyu, and I. King. Where you like to go next: Successive point-of-interest recommendation. In Proceedings of the Twenty-Third international joint conference on Artificial Intelligence, pages 2605–2611. AAAI Press, 2013.
      Google ScholarLocate open access versionFindings
    • E. Cho, S. A. Myers, and J. Leskovec. Friendship and mobility: user movement in location-based social networks. In Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1082–1090. ACM, 2011.
      Google ScholarLocate open access versionFindings
    • L. De Lathauwer, B. De Moor, and J. Vandewalle. A multilinear singular value decomposition. SIAM journal on Matrix Analysis and Applications, 21(4):1253–1278, 2000.
      Google ScholarLocate open access versionFindings
    • G. Druck, G. Mann, and A. McCallum. Learning from labeled features using generalized expectation criteria. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pages 595–602. ACM, 2008.
      Google ScholarLocate open access versionFindings
    • R. P. Ebstein, O. Novick, R. Umansky, B. Priel, Y. Osher, D. Blaine, E. R. Bennett, L. Nemanov, M. Katz, and R. H. Belmaker. Dopamine d4 receptor (d4dr) exon iii polymorphism associated with the human personality trait of novelty seeking. Nature genetics, 12(1):78–80, 1996.
      Google ScholarLocate open access versionFindings
    • M. Ester, H.-P. Kriegel, J. Sander, and X. Xu. A density-based algorithm for discovering clusters in large spatial databases with noise. In Kdd, volume 96, pages 226–231, 1996.
      Google ScholarLocate open access versionFindings
    • R. Feng et al. Temporal destination revisit intention: The effects of novelty seeking and satisfaction. Tourism management, 28(2):580–590, 2007.
      Google ScholarLocate open access versionFindings
    • D. W. Fiske and S. R. Maddi. Functions of varied experience. 1961.
      Google ScholarFindings
    • M. Givon. Variety seeking through brand switching. Marketing Science, 3(1):1–22, 1984.
      Google ScholarLocate open access versionFindings
    • J. Hauser, G. J. Tellis, and A. Griffin. Research on innovation: A review and agenda for marketing science. Marketing science, 25(6):687–717, 2006.
      Google ScholarLocate open access versionFindings
    • N. Hurley and M. Zhang. Novelty and diversity in top-n recommendation–analysis and evaluation. ACM Transactions on Internet Technology (TOIT), 10(4):14, 2011.
      Google ScholarLocate open access versionFindings
    • P. Jensen. Network-based predictions of retail store commercial categories and optimal locations. Physical Review E, 74(3):035101, 2006.
      Google ScholarLocate open access versionFindings
    • J. Kivela and J. C. Crotts. Tourism and gastronomy: Gastronomy’s influence on how tourists experience a destination. Journal of Hospitality & Tourism Research, 30(3):354–377, 2006.
      Google ScholarLocate open access versionFindings
    • J. Kivela, R. Inbakaran, and J. Reece. Consumer research in the restaurant environment, part 1: A conceptual model of dining satisfaction and return patronage. International Journal of Contemporary Hospitality Management, 11(5):205– 222, 1999.
      Google ScholarLocate open access versionFindings
    • J. J. Kivelä and C. Y. H. Chu. Delivering quality service: Diagnosing favorable and unfavorable service encounters in restaurants. Journal of Hospitality & Tourism Research, 25(3):251–271, 2001.
      Google ScholarLocate open access versionFindings
    • T. G. Kolda and B. W. Bader. Tensor decompositions and applications. SIAM review, 51(3):455–500, 2009.
      Google ScholarLocate open access versionFindings
    • J. Lafferty, A. McCallum, and F. C. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. 2001.
      Google ScholarFindings
    • J. Lahti, K. Räikkönen, J. Ekelund, L. Peltonen, O. T. Raitakari, and L. Keltikangas-Järvinen. Socio-demographic characteristics moderate the association between drd4 and novelty seeking. Personality and Individual Differences, 40(3):533–543, 2006.
      Google ScholarLocate open access versionFindings
    • M. Leyton, I. Boileau, C. Benkelfat, M. Diksic, G. Baker, and A. Dagher. Amphetamine-induced increases in extracellular dopamine, drug wanting, and novelty seeking: a pet/[11c] raclopride study in healthy men. Neuropsychopharmacology, 27(6):1027–1035, 2002.
      Google ScholarLocate open access versionFindings
    • H. Mamitsuka. Predicting peptides that bind to mhc molecules using supervised learning of hidden markov models. Proteins Structure Function and Genetics, 33(4):460– 474, 1998.
      Google ScholarLocate open access versionFindings
    • G. S. Mann and A. McCallum. Generalized expectation criteria for semi-supervised learning of conditional random fields. 2008.
      Google ScholarFindings
    • S. M. McNee, J. Riedl, and J. A. Konstan. Being accurate is not enough: how accuracy metrics have hurt recommender systems. In CHI’06 extended abstracts on Human factors in computing systems, pages 1097–1101. ACM, 2006.
      Google ScholarLocate open access versionFindings
    • M. Miele and J. Murdoch. The practical aesthetics of traditional cuisines: slow food in tuscany. Sociologia Ruralis, 42(4):312–328, 2002.
      Google ScholarLocate open access versionFindings
    • J. Oh, S. Park, H. Yu, M. Song, and S.-T. Park. Novel recommendation based on personal popularity tendency. In 2013 IEEE 13th International Conference on Data Mining, pages 507–516. IEEE, 2011.
      Google ScholarLocate open access versionFindings
    • A. Pizam, G.-H. Jeong, A. Reichel, H. van Boemmel, J. M. Lusson, L. Steynberg, S. Volo, C. Kroesbacher, J. Kucerova, N. Montmany, et al. The relationship between risk-taking, sensation-seeking, and the tourist behavior of young adults: A cross-cultural study. Journal of Travel Research, 42(3):251– 260, 2004.
      Google ScholarLocate open access versionFindings
    • G. V. Rebec, J. R. Christensen, C. Guerra, and M. T. Bardo. Regional and temporal differences in real-time dopamine efflux in the nucleus accumbens during free-choice novelty. Brain research, 776(1):61–67, 1997.
      Google ScholarLocate open access versionFindings
    • B. Roark, M. Saraclar, M. Collins, and M. Johnson. Discriminative language modeling with conditional random fields and the perceptron algorithm. In Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, page 47. Association for Computational Linguistics, 2004.
      Google ScholarLocate open access versionFindings
    • T. Scheffler, R. Schirru, and P. Lehmann. Matching points of interest from different social networking sites. In KI 2012: Advances in Artificial Intelligence, pages 245–248.
      Google ScholarLocate open access versionFindings
    • B. W. Silverman. Density estimation for statistics and data analysis, volume 26. CRC press, 1986.
      Google ScholarFindings
    • C. Song, T. Koren, P. Wang, and A.-L. Barabási. Modelling the scaling properties of human mobility. Nature Physics, 6(10):818–823, 2010.
      Google ScholarLocate open access versionFindings
    • C. Song, Z. Qu, N. Blumm, and A.-L. Barabási. Limits of predictability in human mobility. Science, 327(5968):1018– 1021, 2010.
      Google ScholarLocate open access versionFindings
    • L. Song, D. Kotz, R. Jain, and X. He. Evaluating location predictors with extensive wi-fi mobility data. In INFOCOM 2004. Twenty-third AnnualJoint Conference of the IEEE Computer and Communications Societies, volume 2, pages 1414– 1424. IEEE, 2004.
      Google ScholarLocate open access versionFindings
    • P. A. Weaver, K. W. McCleary, L. Lapisto, and L. T. Damonte. The relationship of destination selection attributes to psychological, behavioral and demographic variables. Journal of Hospitality & Leisure Marketing, 2(2):93–109, 1994.
      Google ScholarLocate open access versionFindings
    • M. Ye, P. Yin, and W.-C. Lee. Location recommendation for location-based social networks. In Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, pages 458–461. ACM, 2010.
      Google ScholarLocate open access versionFindings
    • J. Yuan, Y. Zheng, C. Zhang, W. Xie, X. Xie, G. Sun, and Y. Huang. T-drive: driving directions based on taxi trajectories. In Proceedings of the 18th SIGSPATIAL International conference on advances in geographic information systems, pages 99–108. ACM, 2010.
      Google ScholarLocate open access versionFindings
    • N. J. Yuan, Y. Wang, F. Zhang, X. Xie, and G. Sun. Reconstructing individual mobility from smart card transactions: A space alignment approach. In Data Mining (ICDM), 2013 IEEE 13th International Conference on, pages 877–886. IEEE, 2013.
      Google ScholarLocate open access versionFindings
    • N. J. Yuan, F. Zhang, D. Lian, K. Zheng, S. Yu, and X. Xie. We know how you live: exploring the spectrum of urban lifestyles. In Proceedings of the first ACM conference on Online social networks, pages 3–14. ACM, 2013.
      Google ScholarLocate open access versionFindings
    • F. Zhang, D. Wilkie, Y. Zheng, and X. Xie. Sensing the pulse of urban refueling behavior. In Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing, pages 13–22. ACM, 2013.
      Google ScholarLocate open access versionFindings
    • F. Zhang, N. J. Yuan, D. Lian, and X. Xie. Mining noveltyseeking trait across heterogeneous domains. In Proceedings of the 23rd international conference on World wide web, pages 373–384. International World Wide Web Conferences Steering Committee, 2014.
      Google ScholarLocate open access versionFindings
    • M. Zhang and N. Hurley. Novel item recommendation by user profile partitioning. In Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology-Volume 01, pages 508–515. IEEE Computer Society, 2009.
      Google ScholarLocate open access versionFindings
    • T. Zhang. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In Proceedings of the twenty-first international conference on Machine learning, page 116. ACM, 2004.
      Google ScholarLocate open access versionFindings
    • Y. Zhang, J. Callan, and T. Minka. Novelty and redundancy detection in adaptive filtering. In Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, pages 81–88. ACM, 2002.
      Google ScholarLocate open access versionFindings
    • V. W. Zheng, Y. Zheng, X. Xie, and Q. Yang. Collaborative location and activity recommendations with gps history data. In Proceedings of the 19th international conference on World wide web, pages 1029–1038. ACM, 2010.
      Google ScholarLocate open access versionFindings
    • T. Zhou, Z. Kuscsik, J.-G. Liu, M. Medo, J. R. Wakeling, and Y.-C. Zhang. Solving the apparent diversity-accuracy dilemma of recommender systems. Proceedings of the National Academy of Sciences, 107(10):4511–4515, 2010.
      Google ScholarLocate open access versionFindings
    Your rating :
    0

     

    Tags
    Comments