Skip to main content

Kernel density estimation based factored relevance model for multi-contextual point-of-interest recommendation

Abstract

An automated contextual suggestion algorithm is likely to recommend contextually appropriate and personalized ‘points-of-interest’ (POIs) to a user, if it can extract information from the user’s preference history (exploitation) and effectively blend it with the user’s current contextual information (exploration) to predict a POI’s ‘appropriateness’ in the current context. To balance this trade-off between exploitation and exploration, we propose an unsupervised, generic framework involving a factored relevance model (FRLM), constituting two distinct components, one pertaining to historical contexts, and the other corresponding to the current context. We further generalize the proposed FRLM by incorporating the semantic relationships between terms in POI descriptors using kernel density estimation (KDE) on embedded word vectors. Additionally, we show that trip-qualifiers, (e.g. ‘trip-type’, ‘accompanied-by’) are potentially useful information sources that could be used to improve the recommendation effectiveness. Using such information is not straightforward since users’ texts/reviews of visited POIs typically do not explicitly contain such annotations. We undertake a weakly supervised approach to predict the associations between the review-texts in a user profile and the likely trip contexts. Our experiments, conducted on the TREC Contextual Suggestion 2016 dataset, demonstrate that factorization, KDE-based generalizations, and trip-qualifier enriched contexts of the relevance model improve POI recommendation.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Notes

  1. https://foursquare.com.

  2. https://tripadvisor.com.

  3. https://sites.google.com/site/treccontext/.

  4. https://www.kaggle.com/yelp-dataset/yelp-dataset.

  5. Available at https://www.inf.usi.ch/phd/aliannejadi/data.html.

  6. https://github.com/tmikolov/word2vec.

  7. Available at https://code.google.com/archive/p/word2vec/.

  8. Available at https://nlp.stanford.edu/projects/glove/.

References

  • Aliannejadi, M., & Crestani, F. (2018). Personalized context-aware point of interest recommendation. ACM Trans Inf Syst, 36(4), 45:1-45:28. https://doi.org/10.1145/3231933

    Article  Google Scholar 

  • Aliannejadi, M., Mele, I., & Crestani, F. (2017a). A cross-platform collection for contextual suggestion. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval, ACM, New York, NY, USA, SIGIR ’17, (pp. 1269–1272). https://doi.org/10.1145/3077136.3080752.

  • Aliannejadi, M., Rafailidis, D., & Crestani, F. (2017b). Personalized keyword boosting for venue suggestion based on multiple lbsns. In: European conference on information retrieval, Springer: . (pp. 291–303).

  • Arampatzis, A., & Kalamatianos, G. (2017). Suggesting points-of-interest via content-based, collaborative, and hybrid fusion methods in mobile devices. ACM Trans Inf Syst, 36(3), https://doi.org/10.1145/3125620.

  • Bayomi, M., & Lawless, S. (2016). Adapt\_tcd: An ontology-based context aware approach for contextual suggestion. In: TREC 2016.

  • Bayomi, M., Caputo, A., Nicholson, M., Chakraborty, A., & Lawless, S. (2019). Core: A cold-start resistant and extensible recommender system. In: Proceedings of the 34th ACM/SIGAPP symposium on applied computing, ACM, New York, NY, USA, SAC ’19, (pp. 1679–1682), https://doi.org/10.1145/3297280.3297601.

  • Chakraborty, A. (2017). Exploring search behaviour in microblogs. In: Seventh BCS-IRSG symposium on future directions in information Access, FDIA 2017, 5 September 2017, Barcelona, Spain, https://doi.org/10.14236/ewic/FDIA2017.8.

  • Chakraborty, A. (2018). Enhanced contextual recommendation using social media data. In: The 41st international ACM SIGIR conference on research & development in information retrieval, ACM, New York, NY, USA, SIGIR ’18, (pp. 1455–1455). https://doi.org/10.1145/3209978.3210223.

  • Chakraborty, A., Ganguly, D., Caputo, A., & Lawless, S. (2019). A factored relevance model for contextual point-of-interest recommendation. In: Proceedings of the 2019 ACM SIGIR international conference on theory of information retrieval, ACM, New York, NY, USA, ICTIR ’19, (pp. 157–164), https://doi.org/10.1145/3341981.3344230.

  • Chakraborty, A., Ganguly, D., & Conlan, O. (2020a). Relevance models for multi-contextual appropriateness in point-of-interest recommendation. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, association for computing machinery, New York, NY, USA, SIGIR ’20, (pp. 1981–1984), https://doi.org/10.1145/3397271.3401197.

  • Chakraborty, A., Ganguly, D., & Conlan, O. (2020b). Retrievability based document selection for relevance feedback with automatically generated query variants. In: Proceedings of the 29th ACM international conference on information and knowledge management, association for computing machinery, New York, NY, USA, CIKM ’20, (pp. 125–134). https://doi.org/10.1145/3340531.3412032.

  • Chen, L., Chen, G., & Wang, F. (2015). Recommender systems based on user reviews: the state of the art. User Modeling and User-Adapted Interaction, 25(2), 99–154.

    MathSciNet  Article  Google Scholar 

  • Cheng, C., Yang, H., King, I., & Lyu, M. R. (2012). Fused matrix factorization with geographical and social influence in location-based social networks. In: Proceedings of the twenty-sixth AAAI conference on artificial intelligence, AAAI Press, AAAI ’12, (pp. 17–23).

  • Cleverdon, C. (1997). The Cranfield Tests on Index Language Devices (pp. 47–59). San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.

    Google Scholar 

  • Dean-Hall, A., Clarke, C. L. A., Kamps, J., Thomas, P., & Voorhees, E. M. (2012). Overview of the TREC 2012 contextual suggestion track. In: Proceedings of The twenty-first text REtrieval conference, TREC 2012, Gaithersburg, Maryland, USA, November 6-9, 2012, http://trec.nist.gov/pubs/trec21/papers/CONTEXTUAL12.overview.pdf.

  • Dean-Hall, A., Clarke, C. L., Kamps, J., Thomas, P., Simone, N., & Voorhees, E. (2013). Overview of the trec 2013 contextual suggestion track. In: Proceedings of TREC.

  • Dean-Hall, A., Clarke, C. L., Kamps, J., Kiseleva, J., Voorhees, E. M. (2015). Overview of the trec 2015 contextual suggestion track. In: Proceedings of TREC, (vol 2015).

  • Dehghani, M., Kamps, J., Azarbonyad, H., & Marx, M. (2016). Significant words language models for contextual suggestion. In: TREC.

  • Deveaud, R., Albakour, M. D., Macdonald, C., & Ounis, I. (2015). Experiments with a venue-centric model for personalisedand time-aware venue suggestion. In: Proceedings of the 24th ACM international on conference on information and knowledge management, ACM, New York, NY, USA, CIKM ’15, (pp. 53–62), https://doi.org/10.1145/2806416.2806484.

  • Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805.

  • Fang, Q., Xu, C., Hossain, M. S., & Muhammad, G. (2016). Stcaplrs: A spatial-temporal context-aware personalized location recommendation system. ACM Transactions on Intelligent Systems and Technology, 7(4), 59:1-59:30. https://doi.org/10.1145/2842631.

    Article  Google Scholar 

  • Ganguly, D. (2020). Learning variable-length representation of words. Pattern Recognition, 103,107306. https://doi.org/10.1016/j.patcog.2020.107306. https://www.sciencedirect.com/science/article/pii/S0031320320301102.

  • Gao, H., Tang, J., Hu, X., & Liu, H. (2013). Exploring temporal effects for location recommendation on location-based social networks. In: Proceedings of the 7th ACM conference on recommender systems, ACM, New York, NY, USA, RecSys ’13, (pp. 93–100). https://doi.org/10.1145/2507157.2507182.

  • Gemulla, R., Nijkamp, E., Haas, P. J., & Sismanis, Y. (2011). Large-scale matrix factorization with distributed stochastic gradient descent. In: Proceedings of the 17th ACM SIGKDD international conference on knowledge discovery and data mining, association for computing machinery, New York, NY, USA, KDD ’11, (pp. 69–77), https://doi.org/10.1145/2020408.2020426.

  • Ghosh, K., Chakraborty, A., Parui, S. K., & Majumder, P. (2016). Improving information retrieval performance on ocred text in the absence of clean text ground truth. Information processing & management, 52(5), 873 – 884 , https://doi.org/10.1016/j.ipm.2016.03.006. http://www.sciencedirect.com/science/article/pii/S030645731630036X.

  • Griesner, J. B., Abdessalem, T., & Naacke, H. (2015). Poi recommendation: Towards fused matrix factorization with geographical and temporal influences. In: Proceedings of the 9th ACM conference on recommender systems, ACM, New York, NY, USA, RecSys ’15, (pp. 301–304). https://doi.org/10.1145/2792838.2799679.

  • Harman, D. (1996). Overview of the fourth text retrieval conference (trec-4). NIST Special Publication, 500236, 1–23.

    Google Scholar 

  • Hashemi, S. H., Clarke, C. L., Kamps, J., Kiseleva, J., & Voorhees, E. M. (2016a). Overview of the trec 2016 contextual suggestion track. In: Proceedings of TREC, (vol 2016).

  • Hashemi, S. H., Kamps, J., & Amer, N. O. (2016b). Neural endorsement based contextual suggestion. In: TREC.

  • He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T. S. (2017). Neural collaborative filtering. In: Proceedings of the 26th international conference on world wide web, international world wide web conferences steering committee, republic and Canton of Geneva, Switzerland, WWW ’17, (pp. 173–182), https://doi.org/10.1145/3038912.3052569.

  • Jaleel, N. A., Allan, J., Croft, W. B., Diaz, F., Larkey, L. S., Li, X., Smucker, M. D., & Wade, C. (2004). Umass at TREC 2004: Novelty and HARD. In: Proceedings of the thirteenth text REtrieval conference, TREC 2004, Gaithersburg, Maryland, USA, November 16-19, 2004, http://trec.nist.gov/pubs/trec13/papers/umass.novelty.hard.pdf.

  • Jiang, M., & He, D. (2013). Pitt at trec 2013 contextual suggestion track. In: TREC 2013.

  • Khorasani, M., Sadjadi, H., Ramazani, F., & Ensan, F. (2016). A context based recommender system through collaborative filtering and word embedding techniques. In: TREC.

  • Lavrenko, V., & Croft, W. B. (2001). Relevance based language models. In: Proceedings of the 24th annual international ACM SIGIR conference on research and development in information retrieval, ACM, New York, NY, USA, SIGIR ’01, (pp. 120–127). https://doi.org/10.1145/383952.383972.

  • Lavrenko, V., Choquette, M., & Croft, W. B. (2002). Cross-lingual relevance models. In: Proceedings of the 25th annual international ACM SIGIR conference on research and development in information retrieval, association for computing machinery, New York, NY, USA, SIGIR ’02, (pp. 175-182). https://doi.org/10.1145/564376.564408.

  • Levi, A., Mokryn, O., Diot, C., & Taft, N. (2012). Finding a needle in a haystack of reviews: cold start context-based hotel recommender system. In: Proceedings of the sixth ACM conference on recommender systems, ACM, New York, NY, USA, RecSys ’12, (pp. 115–122). https://doi.org/10.1145/2365952.2365977.

  • Li, H., & Alonso, R. (2014). User modeling for contextual suggestion. In: TREC 2014.

  • Li, H., Yang, Z., Lai, Y., Duan, L., & Fan, K. (2014). Bjut at trec 2014 contextual suggestion track: Hybrid recommendation based on open-web information. In: TREC 2014.

  • Li, X., Han, D., He, J., Liao, L., & Wang, M. (2019). Next and next new poi recommendation via latent behavior pattern inference. ACM Transactions on Information and Systems, 37(4), https://doi.org/10.1145/3354187.

  • Liu, B., Fu, Y., Yao, Z., & Xiong, H. (2013). Learning geographical preferences for point-of-interest recommendation. In: Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining, association for computing machinery, New York, NY, USA, KDD ’13, (pp. 1043–1051). https://doi.org/10.1145/2487575.2487673.

  • Liu, X., & Croft, W. B. (2002). Passage retrieval based on language models. In: Proceedings of the eleventh international conference on information and knowledge management, association for computing machinery, New York, NY, USA, CIKM ’02, (pp. 375-382), https://doi.org/10.1145/584792.584854.

  • Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:190711692.

  • Lv, Y., & Zhai, C. (2009). A comparative study of methods for estimating query language models with pseudo feedback. In: Proceedings of the 18th ACM conference on information and knowledge management, ACM, New York, NY, USA, CIKM ’09, (pp. 1895–1898). https://doi.org/10.1145/1645953.1646259.

  • Manotumruksa, J., Macdonald, C., & Ounis, I. (2016). Modelling user preferences using word embeddings for context-aware venue recommendation. arXiv preprint arXiv:160607828.

  • Mihalcea, R., & Tarau, P. (2004). Textrank: bringing order into text. In: Proceedings of the 2004 conference on empirical methods in natural language processing (pp. 404–411).

  • Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th international conference on neural information processing systems - Volume 2, Curran Associates Inc., USA, NIPS’13, (pp. 3111–3119). http://dl.acm.org/citation.cfm?id=2999792.2999959.

  • Miyahara, K., & Pazzani, M. J. (2000). Collaborative filtering with the simple bayesian classifier. In: Proceedings of the 6th pacific rim international conference on artificial intelligence, Springer-Verlag, Berlin, Heidelberg, PRICAI ’00, (pp. 679–689).

  • Musat, C. C., Liang, Y., & Faltings, B. (2013). Recommendation using textual opinions. In: Proceedings of the twenty-third international joint conference on artificial intelligence, AAAI Press, IJCAI ’13, (pp. 2684–2690).

  • Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: global vectors for word representation. In: Empirical methods in natural language processing (EMNLP), (pp. 1532–1543), http://www.aclweb.org/anthology/D14-1162.

  • Roy, D., Bandyopadhyay, A., & Mitra, M. (2013). A simple context dependent suggestion system. In: TREC 2013.

  • Roy, D., Ganguly, D., Mitra, M., & Jones, G. J. (2016). Word vector compositionality based relevance feedback using kernel density estimation. In: Proceedings of the 25th ACM international on conference on information and knowledge management, ACM, New York, NY, USA, CIKM ’16, (pp. 1281–1290). https://doi.org/10.1145/2983323.2983750.

  • Roy, D., Ganguly, D., Bhatia, S., Bedathur, S., & Mitra, M. (2018). Using word embeddings for information retrieval: How collection and term normalization choices affect performance. In: Proceedings of the 27th ACM international conference on information and knowledge management, association for computing machinery, New York, NY, USA, CIKM ’18, (pp. 1835–1838), https://doi.org/10.1145/3269206.3269277.

  • Samar, T., Bellogín, A., & de Vries, A. P. (2016). The strange case of reproducibility versus representativeness in contextual suggestion test collections. Information Retrieval Journal, 19(3), 230–255.

    Article  Google Scholar 

  • Shaw, J. A., & Fox, E. A. (1994). Combination of multiple searches. In: The second text REtrieval conference (TREC-2), (pp. 243–252).

  • Steck, H. (2011). Item popularity and recommendation accuracy. In: Proceedings of the fifth ACM conference on recommender systems, association for computing machinery, New York, NY, USA, RecSys ’11, (pp. 125–132). https://doi.org/10.1145/2043932.2043957.

  • Suglia, A., Greco, C., Musto, C., de Gemmis, M., Lops, P., & Semeraro, G. (2017). A deep architecture for content-based recommendations exploiting recurrent neural networks. In: Proceedings of the 25th conference on user modeling, adaptation and personalization, association for computing machinery, New York, NY, USA, UMAP ’17, (pp. 202–211), https://doi.org/10.1145/3079628.3079684.

  • Voorhees, E., & Harman, D. (1999). Overview of the eighth text retrieval conference (trec-8). In: TREC.

  • Yang, P., & Fang, H. (2012). An exploration of ranking-based strategy for contextual suggestion. In: TREC 2012.

  • Ye, M., Yin, P., Lee, W. C., & Lee, D. L. (2011). Exploiting geographical influence for collaborative point-of-interest recommendation. In: Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval, ACM, New York, NY, USA, SIGIR ’11, (pp. 325–334), https://doi.org/10.1145/2009916.2009962.

  • Yu, Y., & Chen, X. (2015). A survey of point-of-interest recommendation in location-based social networks. In: Workshops at the twenty-ninth AAAI conference on artificial intelligence.

  • Yuan, Q., Cong, G., Ma, Z., Sun, A., & Thalmann, N. M. (2013). Time-aware point-of-interest recommendation. In: Proceedings of the 36th international ACM SIGIR conference on research and development in information retrieval, ACM, New York, NY, USA, SIGIR ’13, (pp. 363–372). https://doi.org/10.1145/2484028.2484030.

  • Zhang, J. D., & Chow, C. Y. (2015). Geosoca: Exploiting geographical, social and categorical correlations for point-of-interest recommendations. In: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, association for computing machinery, New York, NY, USA, SIGIR ’15, (pp. 443–452). https://doi.org/10.1145/2766462.2767711.

Download references

Acknowledgements

This work was supported by the ADAPT Centre for Digital Content Technology, funded under the Science Foundation Ireland Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Anirban Chakraborty.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Chakraborty, A., Ganguly, D., Caputo, A. et al. Kernel density estimation based factored relevance model for multi-contextual point-of-interest recommendation. Inf Retrieval J 25, 44–90 (2022). https://doi.org/10.1007/s10791-021-09400-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10791-021-09400-9

Keywords

  • Relevance model
  • Contextual recommendation
  • User preference model
  • Word-tag semantics
  • Word embedding
  • Kernel density estimation