Academia.eduAcademia.edu
All Topics
Computer Science
Artificial Intelligence
Group Recommendation

Group Recommendation

description18 papers
group11 followers
lightbulbAbout this topic
Group Recommendation is a subfield of recommender systems that focuses on providing personalized suggestions to a group of users, taking into account the preferences and interests of all group members. It aims to optimize the relevance and satisfaction of recommendations for collective decision-making.
lightbulbAbout this topic
Group Recommendation is a subfield of recommender systems that focuses on providing personalized suggestions to a group of users, taking into account the preferences and interests of all group members. It aims to optimize the relevance and satisfaction of recommendations for collective decision-making.
How to Improve Group Homogeneity in Online Social Networks
by Domenico Rosaci

2025

The formation and evolution of interest groups in Online Social Networks is driven by both the users' preferences and the choices of the groups' administrators. In this context, the notion of homogeneity of a social group is crucial: it... more
descriptionView Paperarrow_downwardDownload
A User-Study on Context-aware Group Recommendation for Concerts
by John Krogstie

2025

In this paper, we present a prototype of a group recommendation system for concerts. The prototype is context sensitive taking the user's location and time into account when giving recommendations. The prototype implements three... more
descriptionView Paperarrow_downwardDownload
Towards creating a non-synthetic group recommendation dataset
by Cynthia Liem

2024, Conference on Recommender Systems

Recommender systems can be useful in group settings, e.g. when choosing a movie to watch with a group. However, while considerable research in group recommendation has been performed, we still lack truly ecological datasets on group... more
descriptionView Paperarrow_downwardDownload
Towards Creating a Non-synthetic Group Recommendation Dataset
by Cynthia Liem

2024

Recommender systems can be useful in group settings, e.g. when choosing a movie to watch with a group. However, while considerable research in group recommendation has been performed, we still lack truly ecological datasets on group... more
descriptionView Paperarrow_downwardDownload
Elsevier Editorial System(tm) for Decision Support Systems Manuscript Draft Title: an Empirical Study of Natural Noise Management in Group Recommendation Systems Keywords: Recommender Systems Group Recommender Systems Natural Noise Collaborative Filtering Jaén, September 25th, 2016 an Empirical Stud
by Luis Antonio Leon Martinez

2024

Group recommender systems (GRSs) filter relevant items to groups of users in overloaded search spaces using information about their preferences. When the feedback is explicitly given by the users, inconsistencies may be introduced due to... more
descriptionView Paperarrow_downwardDownload
A Group Recommendation Model Using Diversification Techniques
by Amanda Oliveira

2024, Proceedings of the Annual Hawaii International Conference on System Sciences

In daily life groups are formed naturally, such as watching a movie with friends, or going out for dinner. In all these scenarios, using Recommendation Systems can be helpful by suggesting pieces of information (e.g. movies or... more
descriptionView Paperarrow_downwardDownload
An analysis on the impact of geolocation in recommending venues in location-based social networks
by Carlos Paz Rios

2024

The pervasiveness of geo-located devices has opened new possibilities in recommender systems on social networks. In effect, Location-Based Social Networks or LBSNs are a relatively new breed of social networks that let users share their... more
descriptionView Paperarrow_downwardDownload
LearNext: Learning to Predict Tourists Movements
by Ranieri Baraglia

2024, Zenodo (CERN European Organization for Nuclear Research)

In this paper, we tackle the problem of predicting the "next" geographical position of a tourist given her history (i.e., the prediction is done accordingly to the tourist's current trail) by means of supervised learning techniques,... more
descriptionView Paperarrow_downwardDownload
On Learning Prediction Models for Tourists Paths
by Ranieri Baraglia

2024, ACM Transactions on Intelligent Systems and Technology

In this paper, we tackle the problem of predicting the "next" geographical position of a tourist, given her history (i.e., the prediction is done accordingly to the tourist's current trail) by means of supervised learning techniques,... more
descriptionView Paperarrow_downwardDownload
Deep-Reinforcement-Learning-Based Planner for City Tours for Cruise Passengers
by Giovanni Paragliola

2023, Algorithms

The increasing popularity of cruise tourism has led to the need for effective planning and management strategies to enhance the city tour experience for cruise passengers. This paper presents a deep reinforcement learning (DRL)-based... more
descriptionView Paperarrow_downwardDownload
Deep-Reinforcement-Learning-Based Planner for City Tours for Cruise Passengers
by Giovanni Paragliola

2023, Algorithms

The increasing popularity of cruise tourism has led to the need for effective planning and management strategies to enhance the city tour experience for cruise passengers. This paper presents a deep reinforcement learning (DRL)-based... more
descriptionView Paperarrow_downwardDownload
Deep-Reinforcement-Learning-Based Planner for City Tours for Cruise Passengers
by Claudia Di Napoli

2023, Algorithms

The increasing popularity of cruise tourism has led to the need for effective planning and management strategies to enhance the city tour experience for cruise passengers. This paper presents a deep reinforcement learning (DRL)-based... more
descriptionView Paperarrow_downwardDownload
On group recommendation supported by a minimum cost consensus model
by Jorge Castillo Castro

2023, Data Science and Knowledge Engineering for Sensing Decision Support

Group recommender systems (GRSs) have recently attracted the attention from researchers and industry. They focused on recommending items which satisfy the global preferences of a group, being TV programs and holidays packages typical... more
descriptionView Paperarrow_downwardDownload
Group Recommendations Based on Hesitant Fuzzy Sets
by Jorge Castillo Castro

2023, International Journal of Intelligent Systems

Group recommender systems (GRSs) recommend items that are used by groups of people because certain activities, such as listening to music, watching a movie, dining in a restaurant, etc., are social events performed by groups of people... more
descriptionView Paperarrow_downwardDownload
A Systematic Review of Interaction Design Strategies for Group Recommendation Systems
by Oscar Alvarado

2023, Proceedings of the ACM on Human-Computer Interaction

Systems involving artificial intelligence (AI) are protagonists in many everyday activities. Moreover, designers are increasingly implementing these systems for groups of users in various social and cooperative domains. Unfortunately,... more
descriptionView Paperarrow_downwardDownload
An enhanced hybridized approach for group recommendation via reliable ratings
by Rachna Behl

2023, Indonesian Journal of Electrical Engineering and Computer Science

A group recommender system aim's to provide relevant information to all members of the group. To determine group preferences, the majority of existing studies use aggregation approaches. An aggregation method is a strategy for... more
descriptionView Paperarrow_downwardDownload
Dominance Weighted Social Choice Functions for Group Recommendations
by Antonio Caso

2023, ADCAIJ: ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL

In travel domains, decision support systems provide support to tourists in the planning of their vacation. In particular, when the number of possible Points of Interest (POI) to visit is large, the system should help tourists providing... more
descriptionView Paperarrow_downwardDownload
Tour recommendation for groups
by Reem Atassi

2023, Data Mining and Knowledge Discovery

Consider a group of people who are visiting a major touristic city, such as NY, Paris, or Rome. It is reasonable to assume that each member of the group has his or her own interests or preferences about places to visit, which in general... more
descriptionView Paperarrow_downwardDownload
On group recommendation supported by a minimum cost consensus model
by Jorge E Regalado Castro

2023, Data Science and Knowledge Engineering for Sensing Decision Support

Group recommender systems (GRSs) have recently attracted the attention from researchers and industry. They focused on recommending items which satisfy the global preferences of a group, being TV programs and holidays packages typical... more
Fig. 1. General scheme of the proposal. The use of the minimum cost consensus model in the context of group rec- ommendation, to reach a higher consensus level in the final recommenda- tions and improve the recommendation acceptance, consists of the following phases: (i) Individual recommendation generation, (ii) Borda count-based ranking, and (iii) Minimum cost consensus analysis.
Table 1. Evaluation results according to AUC. Larger values indicate better performance. Table 2. Evaluation results according to MAE. Smaller values indicate better performance.
Overall, the performance values show that the consensus model could influence the GRS behavior, and that it could lead to the improvement of the recommendation performance. Further work will do a deeper explo- ration of the relation between the nature of the GRS data and the consensus reaching process to get a better justification of the obtained performance. Other consensus reaching models will be also explored.
descriptionView Paperarrow_downwardDownload
Group Recommendations Based on Hesitant Fuzzy Sets
by Jorge E Regalado Castro

2023, International Journal of Intelligent Systems

Group recommender systems (GRSs) recommend items that are used by groups of people because certain activities, such as listening to music, watching a movie, dining in a restaurant, etc., are social events performed by groups of people... more
descriptionView Paperarrow_downwardDownload
Optimization approaches to support the planning and analysis of travel itineraries
by Admilson Silva

2022, Expert Systems with Applications

This paper addresses the problem of elaborating travel itineraries considering the visitors´profiles, travel distances and costs. Other parameters such as how much the tourists value the attractions offered are particularly taken into... more
descriptionView Paperarrow_downwardDownload
An enhanced hybridized approach for group recommendation via reliable ratings
by Indonesian Journal of Electrical Engineering and Computer Science

2022, Indonesian Journal of Electrical Engineering and Computer Science

A group recommender system aim's to provide relevant information to all members of the group. To determine group preferences, the majority of existing studies use aggregation approaches. An aggregation method is a strategy for... more
descriptionView Paperarrow_downwardDownload
Multi-Objective Trip Planning With Solution Ranking Based on User Preference and Restaurant Selection
by Naruemon Wattanapongsakorn

2022, IEEE Access

The tourist trip design problem (TTDP) helps the trip planners, such as tourists, tour companies, and government agencies, automate their trip planning. TTDP solver chooses and sequences an optimal subset of point of interest (POIs),... more
descriptionView Paperarrow_downwardDownload
A Group Recommendation Model Using Diversification Techniques
by Amanda Oliveira

2022, Proceedings of the Annual Hawaii International Conference on System Sciences

Figure 1: Ensemble aggregation techniques individual’s preferences.
Figure 2: Ensemble diversification algorithms over recommendations. In _ particular, this proposal evaluated two diversification approaches from the literature: Bounded Random Selection and Bounded Greedy Selection. Figure 2 shows the outputs from these algorithms given a list of recommendations. Additionally, we also evaluated the diversification approach from the baseline [6].
a group G composed by 5 members, uz, w2, U3, U4, and us, being recommended with the item 7, that is the movie Moulin Rouge. Figure 4: Flow of proposed model defined in steps. Figure 4 presents the recommendation flow. The first step is related to obtaining information from the dataset. On the next step, that information is cleaned and prepossessed aiming to reduce noise and improve similarity calculus between items. On Step 3, the group is formed accordingly with a group formation model. In a sequence, the aggregation technique is applied to create the group profile. Then, the recommendations are generated as illustrated in Step 4. Diversification occurs in Step 5. Finally, Step 6 is responsible for evaluating the group recommendations. In the following, the Steps 3, 4, and 5 are particularly discussed as follows.
Figure 3: Illustration of a group G with n=5 users.
Figure 5: Group profile generation flow using aggregation techniques. Once the group is created, the next step is to define the group profile. In this phase, aggregation techniques are applied to individual preferences. Nevertheless, the group preferences matrix must be created, which consists of items that are rated by at least one group member. Figure 5 illustrates such a matrix.
Figure 6: Impact of diversification on top-k.
First we present the precision scores of aggregation techniques for the following approaches GD (Greedy), We generate groups profile based on some predictions, what leads to an uncertain in the ground-truth for groups. As groups are synthetically generated, we made an adaptation to evaluate precision on the experiment. We define the condition that the relevant recommendations are those with higher score than the global mean of evaluated movies [8].
RD (Bounded Random), and SD (Standard). The overall best performance of aggregation techniques occurs in the GD as seen in Figure 7. The AWM score steadily increases over 0.5. Furthermore, the precision decreases from 0.68 (p@3) to 0.4 (p@10) when the MP technique is tested. The LM technique score increases, reaching 0.4. As to the RD approach, as seen in Figure 8, all three technique scores perform under 0.4 at p@3, p@5, and p@10. Figure 9 shows the SD approach with no diversification. Both AWM and MP scores start well at p@3 but then decline at p@ 10. Figure 10: ILD results calculated for different groups and approaches.
Figure 10 demonstrates the ILD scores obtained by four approaches in five different groups. The black line in the top of bars represents the standard deviation error (std). For the groups G2, G3, and G4, the GD approach performs better than BL even considering the std. For G1, both BL and GD approaches achieve similar results scoring 0.9694 and 0.9739 respectively. G5 is the only group where BL performs better than GD. The RD approach performs lower scores than the GD in all groups. It is also noticeable that RD presents a much higher std score than GD, achieving the top score of 8,5% on std. The SD approach achieves the worst ILD results from all approaches. This outcome is somehow expected because this is the only approach that does not implement diversity. Overall, the GD approach achieves the closest result to the BL. Figure 11: Precision at 10 calculated in different groups and approaches.
Figure 12: Precision scores aggregated by diversification approaches.
descriptionView Paperarrow_downwardDownload
Heuristics for the time dependent team orienteering problem: Application to tourist route planning
by Grammati Pantziou

2022, Computers & Operations Research

The Time Dependent Team Orienteering Problem with Time Windows (TDTOPTW) can be used to model several real life problems. Among them, the route planning problem for tourists interested in visiting multiple points of interest (POIs) using... more
Figure 1: Illustration of a tourist route (blue dashed line) from s, to t, via POIs p;, p; and px. Green dashed arrows indicate available multimodal transfer options among POIs.
Figure 2: Arrival time walking and using public transportation
Figure 3: traveling time from u to v as a function of the departure time from u
where wait; denotes the waiting time at POI p, following a visit at p;. Figure 4 illustrates an example of inserting p,, between p; and p; shifting the visit at p; later on time. Figure 4: Illustration of p; insertion between p; and p;.
Figure 6: Illustration of a solution to the TTDP. A typical solution to the TTDP is illustrated in Figure 6. The tourist destination area is partitioned in nine square regions and a central location (representative) is calculated for each region (indicated by green circles). The start/end locations of the route (s1 and ty, respectively) are determined at the user query time and are indicated by the black squares. The representatives 8, (of the area where s; belongs to) and t) (of the area where t, belongs to) are visited in the beginning and in the end of the trip, respectively. POIs pi, pi2, pig and pyi4 are visited in between. Solid and dashed lines denote walking and transit transfers, respectively.
Figure 7: (a) POIs locations and (b) hotels locations, in the Athens metropolitan area.
Figure 8: Illustration of a tourist route starting/ending at a hotel; solid lines indicate walking transfers while dashed lines indicate public transit transfers.
Unlike CSCRoutes, the algorithms introduced in this article, handle time dependent travel times among different locations/POIs. Therefore, they employ different insertion steps than CSCRoutes. Namely, the insertion steps take into account the time dependency of the travel
A pseudo code implementation of the function shift(k, i, 7,r) follows 2, which calculates the insertion cost shift,’ in route r. The function returns oo if te insertion ol pr is infeasible. Apart from inserting a new POI in a route, our algorithms encourage replacing an already included POI by a higher profit POI. Considering that in route r, the POIs p;,p),p; are con- secutive and px is not included in the solution, pz, can replace p; if the arrival at p, takes place within its time window and the time windows of p; and the POIs following p; are not violated. Extending the terminology introduced previously, let shift,’ ; be the difference in the insertion cost from replacing POI p; by px. Then,
3.3 The Time Dependent Slack CSCRoutes (TD_S/CSCR) algorithm The TD_S@CSCR algorithm modifies the insertion step of TD_CSCR i.e., it takes an alter- native approach for determining the POI p,; that will be selected for insertion in a route r. Specifically, while TD_CSCR algorithm’s criterion for selecting the inserted POI in a route is based on the insertion cost, TD_S@€CSCR involves a more global criterion taking into considera- tion the effect of this insertion in the whole route.
Figure 5: Illustration of slack’s duration for POI p;
Table 1: Experimental results when employing the standard profit criterion. As a general remark applied to all algorithms, the increase of the overall collected profit with the increase of the number of routes is sublinear, since the average POI profits is higher when considering low numbers of routes (i.e. for short stays, tourists tend to visit the do-not- miss POIs). Furthermore, all implemented algorithms perform remarkably well with respect to execution time since they derive solutions in less than 0.5 sec in all cases (considering topologies of 113 POIs and up to four routes).
Table 2: Comparison of cluster-based vs. non-cluster-based approaches. Table 3: Improvement from including the i-quality metric
i-quality metric favors the insertion of POIs which belong to clusters with several high-profit POIs, not yet included into a route). Although the table reports only marginal improvement in the case of using the 7-quality metric, this is mostly due to the particular characteristics of the utilized datasets. In particular, the POI clusters of the metropolitan area of Athens are crowded in a relatively restricted geographical area, which allows to easily accessing (by foot or public transit) the most highly profitable POIs one after the other, irrespective of their cluster assignment. This results in deriving almost identical solutions when not incorporating the 7- quality metric, especially for relatively short time budgets. The effect of the i-quality metric is expected to become more evident in scenarios featuring relatively distant clusters and prolonged time budgets.
In the sequel we present experimental results compiled for our TDTOPTW algorithms, using an alternative criterion for selecting the best found solution. Specifically, instead of selecting the solution with the highest aggregate profit over all routes, we select as best found solution the one
descriptionView Paperarrow_downwardDownload
A survey on algorithmic approaches for solving tourist trip design problems
by Grammati Pantziou

2022, Journal of Heuristics

The tourist trip design problem (TTDP) refers to a route-planning problem for tourists interested in visiting multiple points of interest (POIs). TTDP solvers derive daily tourist tours, i.e., ordered visits to POIs, which respect tourist... more
Figure 1: Input data and recommended itineraries in TTDP.
Figure 2: Single-tour TTDP solution approaches (solid arrows denote problem extensions, while dashed arrows denote variants). The OP more closely formulates the single tour version of the TTDP than the other two single-criterion TSPP variants. The vast majority of the papers in the TTDP literature use the OP and its extensions to model different variants of the problem. Therefore, in the sequel of this section we focus on OP, its extensions and variants (see Figure 2) and survey algorithmic approaches for solving them.
Figure 3: OP illustration. Circles’ radius denote nodes’ profit. Given a starting node s, a terminal node t and a positive time limit (budget) B, the goal is to find a path from s to t (or tour if s = t) with length at most B such that the total profit of the visited nodes is maximized (see Figure 3).
The objective function (1) is to maximize the total profit of visited nodes. Constraint (2) ensures that the path starts at node 1 and ends at node N. Constraint (3) ensures that the path starting at node 1 and ending at node N is connected and each node is visited at most once. Constraint (4) ensures that the path meets the time budget. Finally, constraints (5) and (6) ensure that there are no subtours. OP can be formulated as an integer programming problem as follows [127]: Let N be the number of nodes labeled by 1,2,...,N where s=1 andt = WN, p, be the profit of visiting node i and cj; be cost of traveling from i to 7. For every path from 1 to N, if node 2 is followed by node j we set the variable x;; equal to 1 or equal to 0 otherwise. Finally, u; denotes the place of node 7 in the path. With this notation we have the following relations:
Figure 4: OPTW illustration (dashed lines denote the scheduled route, while triangles open- ing/closing times) In OP with Time Windows (OPTW) each node of the graph G can be visited only within one or more specific time intervals (windows) which may be different for each node (see Figure 4). Vansteenwegen et al. [127] argue that time windows significantly affect the nature of OP and its respective algorithmic approaches. For instance, reducing the travel time by reordering scheduled visits, is no longer appropriate due to the time windows. Actually, it has been proved that OPTW is NP-hard even on the line [124].
Figure 5: Multiple-tour TTDP solution approaches (solid arrows denote problem extensions, while dashed arrows denote variants).
Figure 6: TOP illustration. Circles’ radius denote nodes’ profit.
Table 1: Approximation algorithms for the OP
Table 2: Approximation algorithms for the OPTW
Table 3: TOP heuristic algorithms The authors compare their algorithms with TMH and CGW and they show that each of the
Table 4: Comparison of metaheuristic approaches on TOPTW Gavalas et al. recently presented CSCRatio and CSCRoutes, two cluster-based approaches to the TTDP [64]. The main incentive behind these approaches is to favor visits to topology areas featuring high density of good candidate nodes. Furthermore, they both favor solutions with reduced number of long transfers among nodes, which are associated with public transportation transfers in typical urban settings (such transfers are costly, time consuming and usually less attractive to tourists than short walking transfers). The comparison of CSCRatio over the ILS algorithm demonstrated that CSCRatio achieves higher quality solutions in comparable execution time (especially when considering limited itinerary time budget), while also reducing the average number of transfers. As regards the comparison of CSCRoutes over ILS, this confirmed the prevalence of the former in situations where the reduction of inter-cluster transfers is of critical importance. The lower number of transfers in CSCRoutes is achieved at the expense of slightly ower quality solutions. Furthermore, CSCRoutes achieves the best performance results with respect to execution time, compared to ILS and CSCRatio. Notably, the performance gap of the algorithms over ILS increases when tested on realistic TTDP instances, wherein nodes typically feature wide, overlapping time windows and are located nearby each other, while the daily time budget is 5-10h.
descriptionView Paperarrow_downwardDownload
Approximation Algorithms for P2P Orienteering and Stochastic Vehicle Routing Problem
by Dr K K Shukla

2022

We consider the P2P orienteering problem on general metrics and present a (2+ε) approximation algorithm. In the stochastic P2P orienteering problem we are given a metric and each node has a fixed reward and random size. The goal is to... more
descriptionView Paperarrow_downwardDownload
User Transition Pattern Analysis for Travel Route Recommendation
by Chenyi Zhuang

2022, IEICE Transactions on Information and Systems

A travel route recommendation service that recommends a sequence of points of interest for tourists traveling in an unfamiliar city is a very useful tool in the field of location-based social networks. Although there are many web services... more
descriptionView Paperarrow_downwardDownload
Multi-Objective Trip Planning With Solution Ranking Based on User Preference and Restaurant Selection
by supoj Choachaicharoenkul

2022, IEEE Access

The tourist trip design problem (TTDP) helps the trip planners, such as tourists, tour companies, and government agencies, automate their trip planning. TTDP solver chooses and sequences an optimal subset of point of interest (POIs),... more
descriptionView Paperarrow_downwardDownload
Approximation Algorithms for P2P Orienteering and Stochastic Vehicle Routing Problem
by K. K. Shukla

2022

We consider the P2P orienteering problem on general metrics and present a (2+{\epsilon}) approximation algorithm. In the stochastic P2P orienteering problem we are given a metric and each node has a fixed reward and random size. The goal... more
descriptionView Paperarrow_downwardDownload
An Efficient Algorithm for Recommending Personalized Mobile Tourist Routes
by Michael Kenteris

2022

This article deals with the problem of deriving personalized recommendations for daily sightseeing itineraries for tourists visiting any destination. Our approach considers selected places of interest that a traveller would potentially... more
descriptionView Paperarrow_downwardDownload
A hybrid recommendation system for news in a mobile environment
by Paula Viana

2021, Proceedings of the 6th International Conference on Web Intelligence, Mining and Semantics

Over the last few years consumption of news articles has shifted more and more from the written versions towards the web. Mobile devices, which became more powerful, with larger screens and connected to the Internet, have had a great... more
periodically sent to a web server that processes and stores this information.
7. RESULTS AND DISCUSSION Figure 4, 5 and 6 summarize the results obtained in the first experiment. Figure 4 (resulting from the feedback of the first experiment) confirms that the list resulting from the recommendation algorithm was most often chosen, obtaining almost 50% of the total number of selections. The most popular news list comes afterwards, with 29% of the selections and finally the random list. Only a small difference is observed for these two lists, showing that not always the users enjoy popular news. Results are consistent independently of the position of the recommendation list in the experiment, as depicted in Figure 6, showing that there is no bias on the analysis.
Figure 4. Analysis of the recommendation algorithm when compared to simple approaches
Figure 6. Analysis of the influence of the position of the list in the user selection
Figure 7. Rating average associated with each recommendation algorithm
descriptionView Paperarrow_downwardDownload
Improving itinerary recommendations for tourists through metaheuristic algorithms: an optimization proposal
by Angélica de Antonio

2021, IEEE Access

In recent years, recommender systems have been used as a solution to support tourists with recommendations oriented to maximize the entertainment value of visiting a tourist destination. However, this is not an easy task because many... more
descriptionView Paperarrow_downwardDownload
Generating Travel Itinerary Using Ant Collony Optimization
by Pump Head

2021, TELKOMNIKA (Telecommunication Computing Electronics and Control)

Travelling is one of the activities needed b y everyone to overcome weariness. The numb er of information ab out the tourism destination on the internet sometimes does not provide easiness for oncoming tourists. This paper proposes a... more
descriptionView Paperarrow_downwardDownload
Generating Travel Itinerary Using Ant Collony Optimization
by Abdurahman Baizal

2021, TELKOMNIKA (Telecommunication Computing Electronics and Control)

Travelling is one of the activities needed b y everyone to overcome weariness. The numb er of information ab out the tourism destination on the internet sometimes does not provide easiness for oncoming tourists. This paper proposes a... more
descriptionView Paperarrow_downwardDownload
Supporting Human Activities — Exploring Activity-Centered Computing
by Henrik Iskov Christensen

2021, Lecture Notes in Computer Science

In this paper we explore an activity-centered computing paradigm that is aimed at supporting work processes that are radically different from the ones known from office work. Our main inspiration is healthcare work that is characterized... more
descriptionView Paperarrow_downwardDownload
Generating Travel Itinerary Using Ant Collony Optimization
by TELKOMNIKA JOURNAL and 
1 more
Pump Head

2020, TELKOMNIKA Telecommunication Computing Electronics and Control

Travelling is one of the activities needed by everyone to overcome weariness. The number of information about the tourism destination on the internet sometimes does not provide easiness for oncoming tourists. This paper proposes a system... more
descriptionView Paperarrow_downwardDownload
Personalized Itinerary Recommendation with Queuing Time Awareness
by Kwan Hui Lim

2019, Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'17)

Personalized itinerary recommendation is a complex and time-consuming problem, due to the need to recommend popular attractions that are aligned to the interest preferences of a tourist, and to plan these attraction visits as an itinerary... more
descriptionView Paperarrow_downwardDownload
Observing the Work Practices of an Inter-professional Home Care Team: Supporting a Dynamic Approach for Quality Home Care Delivery
by Myriam lewkowicz

2017, COOP 2014 - Proceedings of the 11th International Conference on the Design of Cooperative Systems, 27-30 May 2014, Nice (France)

We are reporting an observational study conducted as part of a larger French research project called PiCADO i . The study explores collaborative activities in work practices of inter-professional teams aiming to deliver quality home care.... more
descriptionView Paperarrow_downwardDownload
Planning sightseeing tours using crowdsensed trajectories
by Chiara Renso

2017, SIGSPATIAL Special

We present an application where semantically enriched trajectories obtained from crowdsensed data are used to build an advanced system for planning personalized sightseeing tours, called TRIPBUILDER. The interesting feature of TRIPBUILDER... more
descriptionView Paperarrow_downwardDownload
On planning sightseeing tours with TripBuilder
by Chiara Renso

2017, Information Processing & Management

We propose TripBuilder, an unsupervised framework for planning personalized sightseeing tours in cities.
descriptionView Paperarrow_downwardDownload
Where shall we go today?
by Chiara Renso

2017, Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13

In this paper we propose TripBuilder, a new framework for personalized touristic tour planning. We mine from Flickr the information about the actual itineraries followed by a multitude of different tourists, and we match these itineraries... more
descriptionView Paperarrow_downwardDownload
TripBuilder: A Tool for Recommending Sightseeing Tours
by Chiara Renso

2017, Lecture Notes in Computer Science

We propose TripBuilder, an user-friendly and interactive system for planning a time-budgeted sightseeing tour of a city on the basis of the points of interest and the patterns of movements of tourists mined from user-contributed data. The... more
descriptionView Paperarrow_downwardDownload
Searching Museum Routes using CBR
by MARIA BELEN DIAZ AGUDO and 
1 more
Jesús Aguirre-Pemán

2016

In this paper, we describe a CBR solution to the route planning problem for groups of people. We have compared keyword coverage results for our CBR approach and heuristic search algorithms. User preferences are important for individual... more
Fig. 1: Museum Graph. The dashed line represents the A* route and the solid line, the Greedy route. Lets see an example to compare the A* and the greedy algorithms with an equivalent heuristic function in action. Let us suppose that we define a map with 9 POIs (i), the input time restriction for a visit t = 15 minutes and the user preferences and the key coverage for each node are described in Table [i]
Table 2: Routes calculated by A* and Greedy algorithm. tr represents the time for completing the route (in both cases do not exceed the t, = 15min). Elapsed CPU time confirms that Greedy runs faster than A* even in a small graph.
Fig. 2: MIGS museum Graph. Red arrows define a route proposed by CBR ap- proach.
Fig. 3: Visualization of the case base as a graph. Line width correlates with the similarity value between linked cases.
Fig. 4: Comparison for different values (time, group size age and preferences) As expec coverage, alt very efficient ted, the greedy algorithm offers better results in terms of keywords hough we see how CBR also exhibits good results in coverage with a response time. Figure [4] (top-left) shows some experimental results obtained when fixing the visit length (t,) in the query. Results show, as expected, that the rou te coverage increases with the time of the visit. 90 minutes give the visitor enough time to visit all the POIs in the museum, so preferences do not affect the route much. However, we observe that CBR keyword coverage is lower in large grou ps even in a 90 minutes visit where all nodes are chosen in the greedy solution. This fact occurs due to the space restrictions that have been captured as knowledge in the cases. The case routes collected show that big groups never stop at the small showcases. This explains why coverage is lower in CBR even when there is time enough to visit all the nodes. Greedy routes do not have knowledge and it generates routes that are uncomfortable for big groups.
On each iteration, the greedy algorithm selects the node that best fits the user preferences in the least amount of time, considering the time spent to arrive at the node and the time visiting it: A Greedy algorithm, unlike the aforementioned A*, just takes into account a heuristic function h(n), the evaluation function that estimates the cost for the current node n (meaning we are evaluating the best path traversing n). We have defined a greedy algorithm, whose main idea is to generate a sorted list with the best nodes according to the user preferences. Finally, we sort the route so the museum can be visited in order.
With a CBR (Case Based Reasoning) approach, we face the problem resolu- tion with a different perspective. Given a query, CBR reuses previous solutions (i.e. routes) that are stored in a case base. Solutions are reused when a simila1 situation occurs [I]. With this approach, we need to deal with a definition of an appropriate similarity measure. Besides, CBR uses a method of solution adapta- tion if the case solution does not fulfil the query restrictions. For example, valid adaptation methods for our problem could be deleting nodes in the final route or adjusting the time in each node to fulfil the query time.
descriptionView Paperarrow_downwardDownload
An Efficient Algorithm for Recommending Personalized Mobile Tourist Routes
by Charalampos Konstantopoulos

2016

This article deals with the problem of deriving personalized recommendations for daily sightseeing itineraries for tourists visiting any destination. Our approach considers selected places of interest that a traveller would potentially... more
descriptionView Paperarrow_downwardDownload
Tour recommendation for groups
by Adriano Fazzone and 
1 more
Reem Atassi

2016

Consider a group of people who are visiting a major touristic city, such as NY, Paris, or Rome. It is reasonable to assume that each member of the group has his or her own interests or preferences about places to visit, which in general... more
descriptionView Paperarrow_downwardDownload
Planning sightseeing tours using crowdsensed trajectories
by Igo Brilhante

2016, SIGSPATIAL Special

We present an application where semantically enriched trajectories obtained from crowdsensed data are used to build an advanced system for planning personalized sightseeing tours, called TRIPBUILDER. The interesting feature of TRIPBUILDER... more
Figure 1: Architecture of TRIPBUILDER. We outline the four layers of the system, i.e. Stream Layer, Batch Layer, Distributed Data Storage and TripBuilder Engine.
Figure 2: Layers of TRIPBUILDER architecture: Stream layer processes incoming data; Batch layer is responsi- ble for processing and transforming data to TRIPBUILDER Engine.
Figure 3: Application of the Stream and the Batch Layer to raw data from Flickr and Wikipedia. The result of these two steps is a set of crowdsensed trajectories describing past behavior of tourists in a geographic area.
Figure 4: A screenshot of the Web interface that lets users interact with TRIPBUILDER. The targeted city is initially selected (a). The drop-down menu on the left helps specify their preferences, the time budget and the personalization factor (b). On the right, a summary of the tour is proposed. Each Pol in the summary comes with a photo and a set of useful information (i.e., visiting time, categories, etc.).
descriptionView Paperarrow_downwardDownload
On planning sightseeing tours with TripBuilder
by Igo Brilhante

2016, Information Processing & Management

We propose TripBuilder, an unsupervised framework for planning personalized sightseeing tours in cities.
Figure 1: Examples of how op(i,k&) modifies the tour according to [(i,k), i.e., the minimum number of endPols connections between 7 and k. lashed line) we arrive at (k,n(k)) (red dashed line), as shown in Figure 1 (a) below. PROOF. Given two endPols i,k, I(i,&) can be either even or odd. First, suppose [(i,&) is even. It means
Figure 2: Overview of the unsupervised process used to build the TripBuilder knowledge base. and time budget that are finally scheduled on the user agenda by the fourth component “Scheduling” In order to assess TRIPBUILDER we generate - in a complete unsupervised process - a knowledge ba
Figure 3: Plot (a) shows the probability distribution of the inter-arrival time for pairs of consecutive photos taken in Rome, Florence, and Pisa. The vertical lines highlight the time thresholds corresponding to P(x < 6) =0.9. Plots (b), (c), (d) show instead the distribution of trajectories length (as number of Pols crossed), the popularity of Pols and the popularity of categories in the three datasets. smallest city of Pisa it decreases to about 3 hours. Traveling time estimation. An important aspect of TRIPBUILDER is that we recommend sightseeing
Figure 4: Average path costs of the techniques employed to solve TRAJSP as a function of the budget. inter-trajectory connections. Efficiency. We now report results of experiments conducted to evaluate the efficiency of TRIPBUILDER as connection cost lower than 0.3. On the other hand, our Local Search algorithm always outperforms both
Figure 5: Average total runtime as a function of the time budget for each city. Bottom bars refer to the average TRIPCOVER runtime while upper bars refer to the average TRAJSP runtime.
Figure 6: Average runtime of Nearest Trajectory and Local Search by varying the time budget. 6. Related Work Several works in the literature propose methods to recommend a list of Pols based on the actual location
Table 1: Statistics regarding the three cities in our dataset.
Table 2: Top-3 most popular Pols and Categories in Pisa, Florence, and Rome. We also report three examples of trajectories per city extracted from the dataset. budget and the parameter a affecting the contribution of Pols/user-similarity and Pol-popularity to user the test users:
Table 3: Evaluation metrics used to assess the effectiveness of TTRIPBUILDER in selecting a set of trajectories of interest for a given user. histories of the users in the test set. Random Selection. Tables 4, 5, and 6 report the effectiveness measured for the recommended sightseeing 1lWe assume the normal daily activity of a tourist in a city to be of twelve hours. Our solution is, however, completely agnostic w.r.t. the daily agenda and works with tourist-provided agenda defining different time slots as well. gs y agi Pp g g
intra-Pol movement time in its solutions. Table 4: Random Selection: average effectiveness of TRIPBUILDER and the baselines in Pisa. In terms of Visiting Time Score (S”), the higher it is, the more relevant the itinerary can be considered As TRIPCOVER takes this factor into account (as a cost), it tends to exploit trajectories containing Pol:
Table 5: Random Selection: average effectiveness of TRIPBUILDER and the baselines in Florence. closer to each other to maximize the user profit. Consequently, we claim that TRIPBUILDER is able to build
Table 6: Random Selection: average effectiveness of TRIPBUILDER and the baselines in Rome. user. For small values of a, results report higher recall values because trajectories crossing popular Pols are prove that the performance of the three techniques are stable w.r.t. different users’ profiles.
Table 7: Profile-based selection: average effectiveness of TRIPBUILDER and the baselines in Rome obtained by exploiting the profiles from Florence visits. reason, we do not consider it in this analysis. Effectiveness — TrajSP. We now evaluate the effectiveness of TRIPBUILDER in scheduling the candidate pages. Finally, it is worth noting that the recall figures computed at the category level are remarkably higher
descriptionView Paperarrow_downwardDownload
Where shall we go today?
by Igo Brilhante

2016, Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13

In this paper we propose TripBuilder, a new framework for personalized touristic tour planning. We mine from Flickr the information about the actual itineraries followed by a multitude of different tourists, and we match these itineraries... more
descriptionView Paperarrow_downwardDownload
TripBuilder: A Tool for Recommending Sightseeing Tours
by Igo Brilhante

2016, Lecture Notes in Computer Science

We propose TripBuilder, an user-friendly and interactive system for planning a time-budgeted sightseeing tour of a city on the basis of the points of interest and the patterns of movements of tourists mined from user-contributed data. The... more
descriptionView Paperarrow_downwardDownload

Related Topics

  • Social Recommender
  • Networked and Social Learning
  • Recommendation Systems
  • Semantic Recommendation
  • Music recommendation
  • Trust-aware Recommender Systems
  • Recommender system, Collaborative filtering
  • Recommeder Systems
  • Music Recommender Systems
  • Social Networks, Recommender Systems
    • Download research papers for free!
    580 California St., Suite 400
    San Francisco, CA, 94104