GrouPlanner

GrouPlanner aims to conduct studies, research and experimentation under the topic of Group Recommender Systems and is meant to support groups of Chinese tourists in every aspect of travel planning and selection of Points of Interest (POI) to visit in the North of Portugal. The system should, in a first instance, aid groups in selection of one (e.g.: hotel, city, etc.) or multiple alternatives (e.g.: POI) from a set of alternatives (according to the preferences and interests of each group member) and in a following step, support each group member along the stay, instilling a greater sense of security. As a result, the system intends to maximize the group satisfaction in several dimensions. The system should be as ubiquitous as possible and consider social and cultural aspects. Artificial Intelligence techniques will be considered and tested. This project involves ISEP, Turismo do Porto e Norte de Portugal, E.R. and Institute of Policy and Management, Chinese Academy of Sciences.
The GrouPlanner project aims to carry out studies, research and experimentation, responding to the challenge of supporting groups of Chinese tourists in the planning and follow-up of visits to the North of Portugal. A diverse set of PhD researchers with experience in each of the areas covered will take part in the project. In addition to the Institute of Engineering of Polytechnic of Porto, that coordinates the project, there will be the participation of the Institute of Policy and Management, Chinese Academy of Sciences and the Turismo do Porto e Norte de Portugal, E.R.. Companies and Associations of Tourism and Cultural Heritage (APHORT - Portuguese Association of Hotels, Restaurants and Tourism, AHRESP - Association of Hospitality, Catering and Similar(s) of Portugal and AHP - Association of Hotels of Portugal) will be granted access to GrouPlanner?s results. The research group involved has a vast trackrecord of ICT projects applied to Tourism, namely the projects TOURSPLAN and PSIS, both funded by FCT, a project with the Porto City Hall and Porto Digital; and projects in the area of argumentation and affective agents (GIGADESSEA and ARGEMOTIONAGENTS) also financed by FCT. In GrouPlanner, a prototype of a Group Recommender System will be developed, for which will be defined/implemented negotiation models and intelligent reports adapted to the defined profiles, context-aware algorithms and metrics of satisfaction. The system should, in the first instance, support groups in selecting one (eg, hotel, city, etc.) or several alternatives (eg Points of Interest), from a set of alternatives (according to the preferences and interests of each element of the group) and, in a second step, support each element of the group during the stay, enhancing a greater sense of safety and comfort. As a result, the system aims to maximize group satisfaction across multiple dimensions. The activities are as follows:

A1 - Literature Review, tourist profiling and POI?s specification.
A2 - GrouPlanner Business Case, Requirements and Architecture.
A3 - Development of the Group Recommender System ? GrouPlanner.
A4 - Pilot Studies and Validation of the GrouPlanner System.
A5 - Organization and Management of the Project.
A6 - Divulgation and Dissemination.

The Priority Axes for Intervention of the Development Strategy of the Plan of Action for Tourism Development in the North of Portugal, namely axis 3 (Marketing and Regional Tourism Promotion) and 5 (Dynamization, Monitoring and Information - Intelligence) will be taken into account. It will also be considered as the main domain the Symbolic Capital, Technologies and Tourism Services of Intelligent Specialization in the North of Portugal. Other domains of RIS3 are also targeted, such as the Resources and Economy of the Sea (nautical tourism), Agro-environmental and Food Systems (local gastronomy) and Life and Health Sciences (Health Tourism and Well-being).
The project is organized in 6 Activities:

A1-Literature Review, tourist profiling and POI?s specification - This Activity consists of reviewing the literature related to the profile of the tourist and group of Chinese tourists, Group Decision Support Systems, Group Recommender Systems, Intelligent Tourism Recommender Systems, argumentation-based negotiation models and satisfaction models. To this end, these tasks will count on the collaboration of the members of the Institute of Policy and Management, Chinese Academy of Sciences, of the doctoral members with experience in projects in the area of tourism and with the fellow who will be part of the project team, who will have background in the area of social sciences. Each of these topics has at least one team member who is a specialist on that topic and who has been following their state of the art over the past few decades.
A2-GrouPlanner Business Case, Requirements and Architecture -In this activity will be carried out in a first task the definition of use cases and the business model; and the second task will be the design of the architecture of the Group Recommender System. The architecture design will consider the goal of developing a system as ubiquitous as possible. This means that the system must be accessible through different types of devices and allow online and offline functionality.
A3-Development of the Group Recommender System ? GrouPlanner- In this activity the prototype of the Group Recommender System will be developed, as well as the models, codes, components, modules, interfaces and other studies that will compose the final solution . The activity encompasses the development/definition/implementation of the multi-agent system, the business model (modeling the profiles of Chinese groups and tourists, points of interest and sensitivity to the context), satisfaction model, negotiation model and intelligent reports.
A4-Pilot Studies and Validation of the GrouPlanner System- This Activity has the objective of discovering weaknesses and potential problems so that they can be solved. The prototype will be evaluated as a whole through case studies to evaluate the system and its components.
A5-Organization and Management of the Project - This activity is carried out throughout the project and aims to ensure good articulation between the participants and the physical and financial execution of the project, while at the same time monitoring the development and delivery of the results proposed by the project.
A6-Divulgation and Dissemination -This activity takes place throughout the project and aims to ensure that the scientific objectives are met and at the same time the disclosure to the stakeholders is duly carried out.
The topic of this project arises naturally both as a way to meet the strategic needs of the region and to take advantage from the opportunity posed by China as it becomes the world?s largest tourist emitter today. China is a country that maintains good relations with Portugal and is developing a middle class with the type of tourist that fits the profile of the target tourist of the northern region of Portugal. In addition, Portugal has to offer many of those that are the interests and items demanded by the Chinese tourist (language, perceptions of safety in travel, cost or Government control (e.g. obtaining a visa), etc.) [1, 2].
GrouPlanner will cover the areas of Business Tourism, City and Short Breaks, Gastronomy, Nature Tourism, Religion Tourism, Heritage, Culture, Health and Well-being, etc. Turism of Porto and Northern Portugal, E.R. has identified many POIs and routes. North region of Portugal has 4 world heritage sites recognized by UNESCO: Historic Centers of Porto and Guimarães cities; Alto Douro Wine Region and Prehistoric Rock Art Sites in the Côa Valley. Several works have been published referring research on intelligent tourism recommender systems [3], with some emphasis on Web-based recommenders [4, 5], mobile devices [6, 7], and the use of context awareness [8]. According to [9], travel recommendation systems aim to match the characteristics of tourism and leisure resources and attractions with the user needs. Systems like TOURSPLAN, developed by members of the research team involved in GrouPlanner proposal [10-12], uses optimization techniques aimed to define and adapt to the visitant?s profile a visit plan combining the most adequate tourism products and points of interest. Some artificial intelligence techniques have been applied to intelligent tourism recommender systems, such as: intelligent agents [13], automated scheduling and route generation [14], heuristics [15], clustering [16], fuzzy logic and Bayesian networks [17], rule-based systems [18], ontologies [19], etc.
The vast majority of existing intelligent tourism recommender systems are targeted at individuals, however tourism or leisure activities are mostly performed by groups [20]. Thus, about a decade ago interest began shifting to investigate recommendation-oriented mechanisms for groups [21-23].
However, the amount of work done on intelligent tourism recommender systems (or Group Recommender Systems - GRS) is quite limited [24]. [25] presented a paper proposing a methodology that seeks to make recommendations using a consensus mechanism. In the accomplishment of this work they used techniques already widely discussed in the literature of Group Decision Making, namely in the development of Group Decision Support Systems. According to [26], GRS are one of the most challenging topics today in the field of recommender systems. GRS draw heavily from existing knowledge in the literature of intelligent tourism recommender systems and Group Decision Support Systems, two topics in which the members of the GrouPlanner project are experts.
In order to support groups in decision making many approaches have been discussed in the literature [27-30]. There is an exponential advance and an increasingly high level of complexity [31-33]. Multi-agent systems have been used to better represent the participants [34, 35]. The use of intelligent agents to represent participants allows participants to be represented not only in relation to their preferences but also in accordance with their intentions [36], personality [37], interests and goals/objectives [38]. In addition, the autonomy inherent to intelligent agents also allows them to be able to perform more complex tasks, such as obtaining information from the environment, being proactive, sharing information and resources, cooperating and coordinating their activities, etc. [39]. Also under the topic of intelligent tourism recommender systems we can find approaches that include multi-agent systems [40-43]. However, several approaches, such as [13, 40, 44] make use of agents to represent: POIs, system components and experts in certain topics (flights, hotels or attractions) using fairly simple types of communications. There are no approaches concerning multi-agent systems capable of representing each of the elements of the group, dealing with their preferences, intentions, relationships with other elements of the group, etc.
As mentioned there are several mechanisms under the topic of intelligent tourism recommender systems with goal of proposing solutions to tourists. However, these mechanisms do not allow to justify options during the "negotiation" process. The use of argumentation-based negotiation models permits overcoming this problem. The main idea of argumentation-based negotiation is the ability to support offers with justifications and explanations, which play a key role in negotiation settings [45]. So, it allows the participants in the negotiation not only to exchange offers, but also reasons and justifications that support these offers in order to mutually influence their preference relations on the set of offers, and consequently the outcome of the dialogue [45]. Clearly, planning a trip, deciding points to visit, or simply choosing a restaurant to go to dinner in group involves various types of dialogue (in a physical/real context). According to the types of dialogues identified by [46] we can easily perceive that in this kind of decision can be put into practice types such as: persuasion, negotiation, inquiry, information seeking and deliberation. Dialogue systems have also been studied by computer science scientists [47-49]. Modeling dialogues using argumentation is a complex task and the approaches in the literature are still very much oriented towards one-to-one dialogue [50-53]. Even more unprecedent is a model that allows real agents and participants to be included in the same process.
What is the main problem to be dealt with by GrouPlanner project? GrouPlanner aims to conduct studies, research and experimentation under the topic of Group Recommender Systems and is meant to support groups of Chinese tourists in every aspect of travel planning and selection of Points of Interest (POI) to visit in the North of Portugal. Why is the problem important and interesting? This topic is important and, at the same time interesting for two reasons: (1)According to the 8 priority areas of the regional strategy of intelligent specialization of the northern region of Portugal, the topic of tourism is explicitly focused on the domain of "Symbolic Capital, Technologies and Services of Tourism". In addition, the topic of tourism is relevant in the following areas: "Resources and Economy of the Sea" (Nautical Tourism), "Agro-Environmental Systems and Food" (Local Gastronomy); And "Life Sciences and Health" (Health and Wellness Tourism). Considering the strategic document "Plan of Action for the Touristic Development of Northern Portugal", we observed that there are 2 axes related to the objectives of GrouPlanner. The axis nº3 (Marketing and Regional Tourism Promotion) and nº5(Dynamization, Monitoring and Information - Intelligence). In addition, GrouPlanner also meets 2 of the 7 societal challenges proposed for H2020: "Health, Demographic Change and Well-Being" and "Europe in a Changing World - Inclusive, Innovative and Weighted Societies" (through the promotion of European identity, the dynamization of rural areas in northern Portugal and the involvement of communities in activities that boost local business, combat poverty and promote the region and active aging); (2)China is one of the BRIC (Brazil, Russia, India and China), countries and one of the strongest economies in the world. The ability of the Chinese to travel to other countries without great limitations is fairly recent. In 1999, it was only possible for them to travel to a group of nine countries. This list has been growing and by 2014 it was already possible for them to travel to 140 countries. Aside from overcoming these legal issues, nowadays it is emerging a middle class that makes up the target tourist of GrouPlanner. Due to its population size and the end of such constraints, China has become in 2012 the largest emitter of tourists in the world. The Chinese have a natural tradition of traveling in groups, however the current international tourist planning systems are aimed at the individual. Technology, as is the case of mobile devices, plays a prominent role in Chinese tourists, increasing their levels of trust and independence. GrouPlanner intends to facilitate the whole process in order to overcome the negative aspects pointed out by Chinese tourists (language, perceptions of safety in travelling, cost or Government control (e.g. obtaining a visa)). In addition, there is a positive history between Portugal and China, from the Macao process to the recent Chinese government investments in Portuguese public companies. In our institution, we had Chinese researchers under the ?science 2007? for 5 years, where there has always been a positive understanding that allow that today they can collaborate in the GrouPlanner project.

Originality of the objectives and object of study in the light of the state of the art and innovative character?
-In this work, unlike the typical processes of individual recommendation the support and recommendation will be directed to groups.
-Group Recommender System as ubiquitous as possible, with a service-oriented architecture.
-Include social and cultural aspects of groups and of the chinese tourist in satisfaction, negotiation and reporting models.
-Model of satisfaction that considers social and cultural aspects and allows one to predict the final satisfaction of the individual and the group in respect to the various possible solutions. This model should also present a more generic proposal that allows, through the analysis of satisfaction, to be able to compare the capacity to enhance the satisfaction of different negotiation models and Recommender or Support Systems.
-A dynamic argumentation-based dialogue model that allows the tourist to perceive the dialogues made by the agents and that at the same time the agents can use the new arguments inserted by the tourist in the negotiation process. The perception of the argument does not imply that it is relative to the content (text), but rather to its importance in the dialogue.
-Intelligent Reports. To invigorate the study in the form of reporting information while using a Group Recommender System. Literature is very poor in this regard. Group decision making is an ongoing process, involving a number of interactions between decision makers and the system. In this work, we will study how information should be reported to Chinese tourists taking into account their interests and intentions.

How will the project contribute to the development of the State of the Art? What are the new ideas that will allow the team to achieve this goal? The project will contribute to the development of the state of the art in the following ways:
-Development of a Group Recommender System based on a multi-agent system. Here the great innovation resides in the Service-Oriented Architecture pattern that will be used for GRS development. The final system will provide all its functionalities in the form of services, so that they can be consumed by different customers. Thus, the developed clients will not be dependent on operating systems, programming languages or specific devices to be developed.
-Modeling and representation of profiles and groups of Chinese tourists considering social and cultural aspects. Each tourist will be represented by an agent throughout the process. The agent will seek to meet the interests and intentions of the tourist it represents. The agents will be naturally competitive with each other, but at the same time they will seek to cooperate in maximizing the group?s ultimate satisfaction. All this implies the creation of models of behaviors and attitudes of the Chinese tourist both in individual and group form so that they can be applied to the computation.
-Definition of a satisfaction model that functions as a utility function to maximize the satisfaction of each tourist and the group. There is a clear difficulty (in literature) to evaluate the quality of decision or to realize how a Recommender/Support System allows to obtain more satisfactory decisions/Solutions than any other system. In this work, a satisfaction model will be developed to predict the satisfaction of the tourist and of the group in the various possible solutions to the problem. Affective aspects (emotions, mood), credibility, preferences of alternatives and criteria, intentions, etc. will be considered.
-Development of a dialogue model using argumentation. Here argumentation works as an informed exchange of ideas and positions, involving several contributors, arising as a dialogical process. The dialogue carried out by the agents should be perceptible by tourists so that they can understand them and in turn contribute with new arguments that are in turn used by the agents in the negotiation process. This mutual understanding between agents and tourists will result in a dynamic argumentation process. Social and cultural issues should be included in the negotiation model, as well as satisfaction in the form of a utility function. This hypothesis of a dynamic argumentation model constitutes a clear advance for the literature of automatic negotiation.
-Support in the planning and in the accompaniment of the trip in the form of intelligent reports. Here are studied new ways of reporting information to the user, through the creation of algorithms that allow to define the information that should be shown to each tourist according to their interests and intentions, the quantity of information, recommendations during the negotiation process, etc. In addition, these algorithms should also consider social and cultural aspects with the goal of helping tourists to overcome the issues previously identified as impeding to travel to certain foreign countries, such as: different language, fear of getting lost, feeling of insecurity and fear of not being able to find fundamental information. In this case, in addition to the intelligent reports being adapted to a context never before studied, it will also be given a strong contribution to the state of the art regarding new forms of reporting when using GRS to support disperse groups. Why does the research team consider itself capable of achieving the proposed objectives? The elements that comprise the team of this project were specifically chosen to meet the needs of this project. All team members have experience in coordinating projects (notably FCT projects) related to one of the topics of GrouPlanner and all members have several publications in indexed journals on the same topics. The hired PhD must have experience in Support/Recommender Systems, Affective Computing, Automatic Negotiation and Multi-Agent Systems. It must also have a strong scientific production ability, especially in JCR journals. In order to better explore issues related to the social sciences area, a fellow with a degree in psychology and experienced in profiling will be hired. Chen An from Institute of Policy and Management, Chinese Academy of Sciences, will work as our contact in China. He will facilitate to us important informations about Chinese tourists and will create conditions for we can run surveys with graduated students and arrange meetings with other important contacts. Paulo Novais from University of Minho will work as a consultant to give a valuable help in the development of the negotiation model. He was the coordinator of TIARAC project (PTDC/ JUR/71354/2006) under the topic of conflict resolution. Filipa Brandão from Tourism School of IPP will also colaborate in GrouPlanner.