menu
Publications

Find here a (hopefully updated) list of my publications including journals, conferences, and workshops in descending order

Journals

  • Pablo Sánchez, Alejandro Bellogín, Ludovico Boratto. Bias characterization, assessment, and mitigation in location-based recommender systems.
    Data Mining and Knowledge Discovery Journal , Volume , February 2023. Springer. DOI: https://doi.org/10.1007/s10618-022-00913-5

    Journal metrics:
    JCR 2021: 5.406, 36/164 (Information Systems: Q1), 41/145 (Artificial Intelligence: Q2).

    Abstract: "Location-Based Social Networks stimulated the rise of services such as Location-based Recommender Systems. These systems suggest to users points of interest (or venues) to visit when they arrive in a specific city or region. These recommendations impact various stakeholders in society, like the users who receive the recommendations and venue owners. Hence, if a recommender generates biased or polarized results, this affects in tangible ways both the experience of the users and the providers’ activities. In this paper, we focus on four forms of polarization, namely venue popularity, category popularity, venue exposure, and geographical distance. We characterize them on different families of recommendation algorithms when using a realistic (temporal-aware) offline evaluation methodology while assessing their existence. Besides, we propose two automatic approaches to mitigate those biases. Experimental results on real-world data show that these approaches are able to jointly improve the recommendation effectiveness, while alleviating these multiple polarizations."
    Keywords: POI recommendation, Bias Mitigation, Polarization, Temporal evaluation.

  • Pablo Sánchez, Alejandro Bellogín. Point-of-Interest Recommender Systems based on Location-Based Social Networks: A Survey from an Experimental Perspective.
    ACM Computing Surveys , Volume , January 2022. ACM. DOI: https://doi.org/10.1145/3510409

    Journal metrics:
    JCR 2021: 14.324, 3/109 (Computer Science, Theory & Methods: Q1).

    Abstract: "Point-of-Interest recommendation is an increasing research and developing area within the widely adopted technologies known as Recommender Systems. Among them, those that exploit information coming from Location-Based Social Networks (LBSNs) are very popular nowadays and could work with different information sources, which pose several challenges and research questions to the community as a whole. We present a systematic review focused on the research done in the last 10 years about this topic. We discuss and categorize the algorithms and evaluation methodologies used in these works and point out the opportunities and challenges that remain open in the field. More specifically, we report the leading recommendation techniques and information sources that have been exploited more often (such as the geographical signal and deep learning approaches) while we also alert about the lack of reproducibility in the field that may hinder real performance improvements."
    Keywords: Information systems, Retrieval models and ranking, Recommender systems, Retrieval efectiveness.

  • Pablo Sánchez, Alejandro Bellogín. On the effects of aggregation strategies for different groups of users in venue recommendation.
    Information Processing & Management , Volume 58 (5), September 2021. Elsevier. DOI: https://doi.org/10.1016/j.ipm.2021.102609

    Journal metrics:
    JCR 2021: 7.466, 20/164 (Computer Science, Information Systems: Q1).

    Abstract: "Suggesting new venues to be visited by a user in a specific city remains an interesting but challenging problem, partly because of the inherent high sparsity of the data available in location-based social networks (LSBNs). At the same time, in traditional recommender systems, in order to improve their performance in these sparse situations, different techniques have been proposed mainly by augmenting and aggregating the data available in different domains. In this paper, we address the problem of venue recommendation from a novel perspective: we propose two strategies to select a set of candidate cities in order to use their information when performing recommendations for the users in a specific (target) city. In this context, we categorize users into two different groups (tourists and locals) according to their movement patterns and analyze the potential biases in the recommendations received by each of these groups. We provide an experimental comparison of several recommendation algorithms in a temporal split, where we analyze two strategies to select cities and augment the available data: based on the number of interactions and based on the distance with respect to the target city. Our results show that, in general, extending the available data by proximity increases the performance of the majority of the tested recommenders in terms of relevance and coverage, with almost no change in novelty and diversity. We have found that those users belonging to the tourist group tend to obtain better results in terms of relevance. Furthermore, in general, tourists consistently exhibit different performance by some families of recommenders for other evaluation dimensions, evidencing a popularity bias in user behavior and raising potential fairness issues regarding the quality of the received recommendations. We investigate these aspects and provide methods to better understand the problem. We expect these results could provide readers with an overall picture of what can be achieved in a real-world environment."
    Keywords: Venue recommendation, Data augmentation, Temporal evaluation, Tourism, User types, Fairness.

  • Pablo Sánchez, Alejandro Bellogín. Applying reranking strategies to route recommendation using sequence-aware evaluation.
    User Modeling and User-Adapted Interaction , Volume 30 , pp. 659-725, September 2020. Springer. DOI: https://doi.org/10.1007/s11257-020-09258-4

    Journal metrics:
    JCR 2020: 4.412, 5/23 (Computer Science and Cybernetics: Q1).

    Abstract: "Venue recommendation approaches have become particularly useful nowadays due to the increasing number of users registered in location-based social networks (LBSNs), applications where it is possible to share the venues someone has visited and establish connections with other users in the system. Besides, the venue recommendation problem has certain characteristics that differ from traditional recommendation, and it can also benefit from other contextual aspects to not only recommend independent venues, but complete routes or venue sequences of related locations. Hence, in this paper, we investigate the problem of route recommendation under the perspective of generating a sequence of meaningful locations for the users, by analyzing both their personal interests and the intrinsic relationships between the venues. We divide this problem into three stages, proposing general solutions to each case: First, we state a general methodology to derive user routes from LBSNs datasets that can be applied in as many scenarios as possible; second, we define a reranking framework that generate sequences of items from recommendation lists using different techniques; and third, we propose an evaluation metric that captures both accuracy and sequentiality at the same time. We report our experiments on several LBSNs datasets and by means of different recommendation quality metrics and algorithms. As a result, we have found that classical recommender systems are comparable to specifically tailored algorithms for this task, although exploiting the temporal dimension, in general, helps on improving the performance of these techniques; additionally, the proposed reranking strategies show promising results in terms of finding a trade-off between relevance, sequentiality, and distance, essential dimensions in both venue and route" recommendation tasks..
    Keywords: Travel sequences, Route recommendation, Temporal evaluation, Reranking.

  • Pablo Sánchez, Alejandro Bellogín. Time and sequence awareness in similarity metrics for recommendation.
    Information Processing & Management , Volume 57 (3), May 2020. Elsevier. DOI: https://doi.org/10.1016/j.ipm.2020.102228

    Journal metrics:
    JCR 2020: 6.222, 21/162 (Computer Science, Information Systems: Q1).

    Abstract: Modeling the temporal context efficiently and effectively is essential to provide useful recommendations to users. In this work, we focus on improving neighborhood-based approaches where we integrate three different mechanisms to exploit temporal information. We first present an improved version of a similarity metric between users using a temporal decay function, then, we propose an adaptation of the Longest Common Subsequence algorithm to be used as a time-aware similarity metric, and we also redefine the neighborhood-based recommenders to be interpreted as ranking fusion techniques where the neighbor interaction sequence can be exploited by considering the last common interaction between the neighbor and the user.
    Keywords: Recommender systems, Time-aware, Sequence, Neighborhood, Collaborative filtering.

  • Pablo Sánchez, Alejandro Bellogín. Building user profiles based on sequences for content and collaborative filtering.
    Information Processing & Management , Volume 56 (1), pp. 192-211, January 2019. Elsevier. DOI: https://doi.org/10.1016/j.ipm.2018.10.003

    Journal metrics:
    JCR 2019: 4.787, 22/156 (Computer Science, Information Systems: Q1).

    Abstract: Modeling user profiles is a necessary step for most information filtering systems - such as recommender systems - to provide personalized recommendations. However, most of them work with users or items as vectors, by applying different types of mathematical operations between them and neglecting sequential or content-based information. Hence, in this paper we study how to propose an adaptive mechanism to obtain user sequences using different sources of information, allowing the generation of hybrid recommendations as a seamless, transparent technique from the system viewpoint. As a proof of concept, we develop the Longest Common Subsequence (LCS) algorithm as a similarity metric to compare the user sequences, where, in the process of adapting this algorithm to recommendation, we include different parameters to control the efficiency by reducing the information used in the algorithm (preference filter), to decide when a neighbor is considered useful enough to be included in the process (confidence filter), to identify whether two interactions are equivalent (δ-matching threshold), and to normalize the length of the LCS in a bounded interval (normalization functions). These parameters can be extended to work with any type of sequential algorithm. We evaluate our approach with several state-of-the-art recommendation algorithms using different evaluation metrics measuring the accuracy, diversity, and novelty of the recommendations, and analyze the impact of the proposed parameters. We have found that our approach offers a competitive performance, outperforming content, collaborative, and hybrid baselines, and producing positive results when either content- or rating-based information is exploited.
    Keywords: Hybrid recommender systems, Preference filtering, Content-based filtering, Collaborative filtering, Longest Common Subsequence.

  • Alejandro Bellogín, Pablo Sánchez. Collaborative filtering based on subsequence matching: A new approach.
    Information Sciences , Volume 418 , pp. 432-446, December 2017. Elsevier. DOI: https://doi.org/10.1016/j.ins.2017.08.016

    Journal metrics:
    JCR 2017: 4.305, 12/148 (Information Systems: Q1).

    Abstract: Neighbourhood-based techniques, although very popular in recommendation systems, show different performance results depending on the specific parameters being used; besides the neighbourhood size, a critical component of these recommenders is the similarity metric. Therefore, by considering more information associated to the users – such as taking into account the ordering of the items as they were consumed or the whole interaction pattern between users and items – it should be possible to define more complete, and better performing, similarity metrics for collaborative filtering. In this paper, we propose a technique to compare users – also extendable to items –, working with them as sequences instead of vectors, hence enabling a new perspective to analyse the user behaviour by finding other users who have similar sequential patterns instead of focusing only on similar ratings in the items. We also compare our approach with other well-known techniques, showing comparable or better performance in terms of rating prediction, ranking evaluation, and novelty and diversity metrics. According to the results obtained, we believe there is still a lot of room for improvement, due to its generality and the good performance obtained by this technique.
    Keywords: Collaborative Filtering, User Similarity, Longest Common Subsequence, Interaction pattern.
Conferences

  • Pablo Sánchez, Linus W. Dietz. Travelers vs. Locals: The Effect of Cluster Analysis in Point-of-Interest Recommendation.
    30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2022), Barcelona, Spain, ACM July 2022, pp. 132–142. ACM. DOI: https://doi.org/10.1145/3503252.3531320

    Conference rating:
    CORE 2021: rank B
    GGS 2021: class 3, rating B

    Abstract: The involvement of geographic information differentiates point-of-interest recommendation from traditional product recommendation. This geographic influence is usually manifested in the effect of users tending toward visiting nearby locations, but further mobility patterns can be used to model different groups of users. In this study, we characterize the check-in behavior of local and traveling users in a global Foursquare check-in data set. Based on the features that capture the mobility and preferences of the users, we obtain representative groups of travelers and locals through an independent cluster analysis. Interestingly, for locals, the mobility features analyzed in this work seem to aggravate the cluster quality, whereas these signals are fundamental in defining the traveler clusters. To measure the effect of such a cluster analysis when categorizing users, we compare the performance of a set of recommendation algorithms, first on all users together, and then on each user group separately in terms of ranking accuracy, novelty, and diversity. Our results on the Foursquare data set of 139,270 users in five cities show that locals, despite being the most numerous groups of users, tend to obtain lower values than the travelers in terms of ranking accuracy while these locals also seem to receive more novel and diverse POI recommendations. For travelers, we observe the advantages of popularity-based recommendation algorithms in terms of ranking accuracy, by recommending venues related to transportation and large commercial establishments. However, there are huge differences in the respective travelers groups, especially between predominantly domestic and international travelers. Due to the large influence of mobility on the recommendations, this article underlines the importance of analyzing user groups differently when making and evaluating personalized point-of-interest recommendations.
    Keywords: Point-of-Interest recommendation, User Modeling, Human mobility analysis, Offline evaluation.

  • Sergio Torrijos, Alejandro Bellogín, Pablo Sánchez. Discovering Related Users in Location-based Social Networks.
    28th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2020), Online, ACM July 2020, pp. 353-357. ACM. DOI: https://doi.org/10.1145/3340631.3394882

    Conference rating:
    CORE 2020: rank B
    GGS 2018: class 3, rating B

    Abstract: Users from Location-Based Social Networks can be characterised by how and where they move. However, most of the works that exploit this type of information neglect either its sequential or its geographical properties. In this article, we focus on a specific family of recommender systems, those based on nearest neighbours; we define related users based on common check-ins and similar trajectories and analyse their effects on the recommendations. For this purpose, we use a real-world dataset and compare the performance on different dimensions against several state-of-the-art algorithms. The results show that better neighbours could be discovered with these approaches if we want to promote novel and diverse recommendations.
    Keywords: location-based social networks, neighbours, trajectory similarity.

  • Pablo Sánchez, Alejandro Bellogín. Attribute-based evaluation for recommender systems: incorporating user and item attributes in evaluation metrics.
    13th ACM Conference on Recommender Systems, (RecSys 2019), Copenhagen, Denmark, ACM September 2019, pp. 378-382. ACM. DOI: https://doi.org/10.1145/3298689.3347049

    Conference rating:
    CORE 2018: rank B
    GGS 2018: class 2, rating A-

    Abstract: Research in Recommender Systems evaluation remains critical to study the efficiency of developed algorithms. Even if different aspects have been addressed and some of its shortcomings - such as biases, robustness, or cold start - have been analyzed and solutions or guidelines have been proposed, there are still some gaps that need to be further investigated. At the same time, the increasing amount of data collected by most recommender systems allows to gather valuable information from users and items which is being neglected by classical offline evaluation metrics. In this work, we integrate such information into the evaluation process in two complementary ways: on the one hand, we aggregate any evaluation metric according to the groups defined by the user attributes, and, on the other hand, we exploit item attributes to consider some recommended items as surrogates of those interacted by the user, with a proper penalization. Our results evidence that this novel evaluation methodology allows to capture different nuances of the algorithms performance, inherent biases in the data, and even fairness of the recommendations.
    Keywords: Top-N Recommendation, Evaluation, RankingMetrics, Relevance.

  • Pablo Sánchez. Exploiting contextual information for recommender systems oriented to tourism.
    13th ACM Conference on Recommender Systems, (RecSys 2019), Copenhagen, Denmark, ACM September 2019, pp. 601-605. ACM. DOI: https://doi.org/10.1145/3298689.3347062

    Conference rating:
    CORE 2018: rank B
    GGS 2018: class 2, rating A-

    Abstract: The use of contextual information like geographic, temporal (including sequential), and item features in Recommender Systems has favored their development in several different domains such as music, news, or tourism, together with new ways of evaluating the generated suggestions. This paper presents the underlying research in a PhD thesis introducing some of the fundamental considerations of the current tourism-based models, emphasizing the Point-Of-Interest (POI) problem, while proposing solutions using some of these additional contexts to analyze how the recommendations are made and how to enrich them. At the same time, we also intend to redefine some of the traditional evaluation metrics using contextual information to take into consideration other complementary aspects beyond item relevance. Our preliminary results show that there is a noticeable popularity bias in the POI recommendation domain that has not been studied in detail so far; moreover, the use of contextual information (such as temporal or geographical) help us both to improve the performance of recommenders and to get better insights of the quality of provided suggestions.
    Keywords: Recommender Systems, Point-Of-Interest recommendation, Contextual Information, Evaluation.

  • Pablo Sánchez, Alejandro Bellogín. Measuring anti-relevance: a study on when recommendation algorithms produce bad suggestions.
    12th ACM Conference on Recommender Systems, (RecSys 2018), Vancouver British Columbia, Canada, ACM October 2018, pp. 367-371. ACM. DOI: https://doi.org/10.1145/3240323.3240382

    Conference rating:
    CORE 2018: rank B
    GGS 2018: class 2, rating A-

    Abstract: Typically, performance of recommender systems has been measured focusing on the amount of relevant items recommended to the users. However, this perspective provides an incomplete view of an algorithm's quality, since it neglects the amount of negative recommendations by equating the unknown and negatively interacted items when computing ranking-based evaluation metrics. In this paper, we propose an evaluation framework where anti-relevance is seamlessly introduced in several ranking-based metrics; in this way, we obtain a different perspective on how recommenders behave and the type of suggestions they make. Based on our results, we observe that non-personalized approaches tend to return less bad recommendations than personalized ones, however the amount of unknown recommendations is also larger, which explains why the latter tend to suggest more relevant items. Our metrics based on anti-relevance also show the potential to discriminate between algorithms whose performance is very similar in terms of relevance.
    Keywords:

  • Pablo Sánchez, Rus M. Mesas, Alejandro Bellogín. New approaches for evaluation: correctness and freshness: Extended Abstract.
    5th Spanish Conference on Information Retrieval, (CERI 2018), Zaragoza, Spain, ACM June 2018, pp. 14:1-14:2. ACM. DOI: https://doi.org/10.1145/3230599.3230614

    Abstract: The main goal of a Recommender System is to suggest relevant items to users, although other utility dimensions -- such as diversity, novelty, confidence, possibility of providing explanations -- are often considered. In this work, we study two dimensions that have been neglected so far in the literature: coverage and temporal novelty. On the one hand, we present a family of metrics that combine precision and coverage in a principled manner (correctness); on the other hand, we provide a measure to account for how much a system is promoting fresh items in its recommendations (freshness). Empirical results show the usefulness of these new metrics to capture more nuances of the recommendation quality.
    Keywords:

  • Alejandro Bellogín, Pablo Sánchez. Applying Subsequence Matching to Collaborative Filtering: Extended Abstract.
    5th Spanish Conference on Information Retrieval, (CERI 2018), Zaragoza, Spain, ACM June 2018, pp. 5:1-5:2. ACM. DOI: https://doi.org/10.1145/3230599.3230605

    Abstract: Neighbourhood-based approaches, although they are one of the most popular strategies in the recommender systems area, continue using classic similarities that leave aside the sequential information of the users interactions. In this extended abstract, we summarise the main contributions of our previous work where we proposed to use the Longest Common Subsequence algorithm as a similarity measure between users, by adapting it to the recommender systems context and proposing a mechanism to transform users interactions into sequences. Furthermore, we also introduced some modifications on the original LCS algorithm to allow non-exact matchings between users and to bound the similarities obtained in the [0,1] interval. Our reported results showed that our LCS-based similarity was able to outperform different state-of-the-art recommenders in two datasets in both ranking and novelty and diversity metrics.
    Keywords:

  • Pablo Sánchez, Alejandro Bellogín. Time-Aware Novelty Metrics for Recommender Systems.
    40th European Conference on {IR} Research, (ECIR 2018), Grenoble, France, Springer March 2018, pp. 357-370. Springer. DOI: https://doi.org/10.1007/978-3-319-76941-7_27

    Conference rating:
    CORE 2018: rank A
    GGS 2018: class 2, rating A-

    Abstract: Time-aware recommender systems is an active research area where the temporal dimension is considered to improve the effectiveness of the recommendations. Even though performance evaluation is dominated by accuracy-related metrics – such as precision or NDCG –, other properties of the recommended items like their novelty and diversity have attracted attention in recent years, where several metrics have been defined with this goal in mind. However, it is unclear how suitable these metrics are to measure novelty or diversity in temporal contexts. In this paper, we propose a formulation to capture the time-aware novelty (or freshness) of the recommendation lists, according to different time models of the items. Hence, we provide a measure to account for how much a system is promoting fresh items in its recommendations. We show that time-aware recommenders tend to provide more fresh items, although this is not always the case, depending on statistical biases and patterns inherent to the data. Our results, nonetheless, indicate that the proposed formulation can be used to extend the knowledge about what items are being suggested by any recommendation technique aiming to exploit temporal contexts.
    Keywords:

  • Pablo Sánchez, Alejandro Bellogín, Iván Cantador. Studying the Effect of Data Structures on the Efficiency of Collaborative Filtering Systems.
    4th Spanish Conference on Information Retrieval, (CERI 2016), Granada, Spain, ACM June 2016, pp. 8. ACM. DOI: https://doi.org/10.1145/2934732.2934747

    Abstract: Recommender systems is an active research area where the major focus has been on how to improve the quality of generated recommendations, but less attention has been paid on how to do it in an efficient way. This aspect is increasingly important because the information to be considered by recommender systems is growing exponentially. In this paper we study how different data structures affect the performance of these systems. Our results with two public datasets provide relevant insights regarding the optimal data structures in terms of memory and time usages. Specifically, we show that classical data structures like Binary Search Trees and Red-Black Trees can beat more complex and popular alternatives like Hash Tables.
    Keywords:
Workshops

  • Pablo Sánchez, Alejandro Bellogín. A novel approach for venue recommendation using cross-domain techniques.
    Workshop on Intelligent Recommender Systems by Knowledge Transfer and Learning, (RecSysKTL 2018) co-located with 12th International Conference on Recommender Systems (RecSys 2018). Vancouver, Canada, August 2018 .

    Abstract: Finding the next venue to be visited by a user in a specific cityis an interesting, but challenging, problem. Different techniqueshave been proposed, combining collaborative, content, social, andgeographical signals; however it is not trivial to decide which tech-nique works best, since this may depend on the data density or theamount of activity logged for each user or item. At the same time,cross-domain strategies have been exploited in the recommendersystems literature when dealing with (very) sparse situations, suchas those inherently arising when recommendations are producedbased on information from a single city.In this paper, we address the problem of venue recommendationfrom a novel perspective: applying cross-domain recommenda-tion techniques considering each city as a different domain. Weperform an experimental comparison of several recommendationtechniques in a temporal split under two conditions: single-domain(only information from the target city is considered) and cross-domain (information from many other cities is incorporated intothe recommendation algorithm). For the latter, we have exploredtwo strategies to transfer knowledge from one domain to another:testing the target city and training a model with information of thekcities with more ratings or only using thekclosest cities.Our results show that, in general, applying cross-domain byproximity increases the performance of the majority of the recom-menders in terms of relevance. This is the first work, to the bestof our knowledge, where so many domains (eight) are combinedin the tourism context where a temporal split is used, and thus weexpect these results could provide readers with an overall pictureof what can be achieved in a real-world environment.
    Keywords:

  • Pablo Sánchez, Alejandro Bellogín. Challenges on Evaluating Venue Recommendation Approaches: Position Paper.
    Workshop on Recommenders in Tourism, (RecTour 2018) co-located with 12th International Conference on Recommender Systems (RecSys 2018). Vancouver, Canada, August 2018 , pp. 37-40.

    Abstract: Recommender systems are widely used tools in a large number ofonline applications due to their ability to learn the tastes and needsof the users. Venue recommendation approaches have recently be-come particularly useful, and even though these techniques havecertain characteristics that differ from traditional recommendation,they deserve special attention from the research community due tothe increase on the number of applications using tourism informa-tion to perform venue suggestions. In particular, how to properlyevaluate (in an offline setting) this type of recommenders needsto be better analyzed, as they are normally evaluated using stan-dard evaluation methodologies, neglecting their unique features. Inthis paper, we discuss and propose some solutions to two specificaspects around this problem: how to deal with already interactedvenues in the test set and how to incorporate the sequence of vis-ited venues by the user when measuring the performance of analgorithm (i.e., in an evaluation metric).
    Keywords:

  • Pablo Sánchez, Alejandro Bellogín. Revisiting Neighbourhood-Based Recommenders For Temporal Scenarios.
    1st Workshop on Temporal Reasoning in Recommender Systems (RecTemp 2017) co-located with 11th International Conference on Recommender Systems (RecSys 2017). Como, Italy, August 2017 , pp. 40-44.

    Abstract: Modelling the temporal context efficiently and effectively is essen-tial to provide useful recommendations to users. Methods suchas matrix factorisation and Markov chains have been combinedrecently to model the temporal preferences of users in a sequentialbasis. In this work, we focus on Neighbourhood-based Collabo-rative Filtering and propose a simple technique that incorporatesinteraction sequences when producing a personalised ranking. Weshow the efficiency of this method when compared against othersequence- and time-aware recommendation methods under twoclassical temporal evaluation methodologies.
    Keywords:

Website template from: Javier Sanz-Cruzado Puig