Fabiana Lorenzi

A tourism recommender system based on collaboration and text analysis.

This work presents a recommender system that helps travel agents in discovering options for customers, especially those who do not know where to go and what to do. The system analyzes textual messages exchanged between a travel agent and a customer through a private Web chat. Text mining techniques help discover interesting areas in the messages. After that, the system searches a database and retrieves tourist options (like cities and attractions) classified in these interesting areas. The system makes use of a tourism ontology, containing themes and a controlled vocabulary, to identify themes in the textual messages. The system acts as a decision support system, because it does not make recommendations directly to the customer.

Case-based recommender systems: a unifying view

This paper presents a unifying framework to model case-based reasoning recommender systems (CBR-RSs). CBR-RSs have complex architectures and specialize the CBR problem solving methodology in a number of ways. The goal of the proposed framework is to illustrate both the common features of the various CBR-RSs as well as the points were these systems take different solutions. The proposed framework was derived by the analysis of some systems and techniques comprising nine different recommendation functionalities. The ultimate goal of the this framework is to ease the evaluation and the comparison of case-based reasoning recommender systems and to provide a tool to identify open areas for further research.

A multiagent knowledge-based recommender approach with truth maintenance

This thesis investigates a way of using knowledge in dynamic and distributed domains for supporting recommendation, keeping the consistence of the decision knowledge that change over time. We propose the use of a multiagent knowledge-based recommender approach capable of dealing with distributed expert knowledge in order to support travel agents in recommending tourism packages. Agents work as experts cooperating and communicating to each other in the recommendation process. Each agent has a truth maintenance system (TMS) component that helps the agents to keep the integrity of their knowledge bases.

Optimizing Preferences within Groups: A Case Study on Travel Recommendation

This work describes a multiagent recommender system where agents work on behalf of members of a group of customers, trying to reach the best recommendation for the whole group. The goal is to model the group recommendation as a distributed constraint optimization problem, taking customer preferences into account and searching for the best solution. Experimental results show that this approach can be sucessfully applied to propose recommendations to a group of users.

PersonalTour: A Recommender System for Travel Packages

This paper describes the Personal Tour recommender system that helps customers to find best travel packages according to their preferences. Personal Tour is based on the paradigm of the Distributed Artificial Intelligence and a customer recommendation request is divided into partial recommendations that are handled by different agents. Experiments were run with real customers and the results are presented.

Improving recommendations through an assumption-based multiagent approach: An application in the tourism domain

Recommender systems are popular tools dealing with the information overload problem in e-commerce web sites. The more they know about the users, the better recommendations they can provide. However, sometimes, in real situations, it is necessary to make guesses about the value of missing but useful data in order to generate a recommendation immediately, rather than waiting the data becomes available. This paper presents an assumption-based multiagent recommender system capable of making these types of assumptions about the preferences of the users. The approach was validate in the tourism domain (recommendation of travel packages). Experiments were conducted to illustrate the impact of various assumption making strategies on the quality of the recommendations as well as the impact of trust assignment.

A Multiagent Recommender System with Task-Based Agent Specialization

This paper describes a multiagent recommender system where agents maintain local knowledge bases and, when requested to support a travel planning task, they collaborate exchanging information stored in their local bases. A request for a travel recommendation is decomposed by the system into sub tasks, corresponding to travel services. Agents select tasks autonomously, and accomplish them with the help of the knowledge derived from previous solutions. In the proposed architecture, agents become experts in some task types, and this makes the recommendation generation more efficient. In this paper, we validate the model via simulations where agents collaborate to recommend a travel package to the user. The experiments show that specialization is useful hence providing a validation of the proposed model.

Organizations and social networking: Utilizing social media to engage consumers

The modern business landscape demands that organizations maintain an online presence to network with their customers and investors. Therefore, understanding the link between social media and e-business is an important first step in cultivating these internet-based relationships. Organizations and Social Networking: Utilizing Social Media to Engage Consumers provides a broad investigation into the use of social technologies in business practices through theoretical research and practical applications. This book explores the opportunities and challenges brought about by the advent of various 21st century online business web tools and platforms, presenting professionals and researchers in e-business, social marketing, online collaborative communities, and social analytics with cutting-edge information and technological developments to implement in their own enterprises. This book is part of the Advances in Marketing, Customer Relationship Management, and E-Services series collection.

Enhancing the Quality of Recommendations through Expert and Trusted Agents

In multi-agent recommender systems, agents are able to generate recommendations according to the preferences of the customer. However, in some domains, specific knowledge is required in order to compose a recommendation and this knowledge may be not available for the agent. In these cases, agents need to communicate with other agents in the community searching for the specific information to complete the recommendation. This paper presents a multi-agent recommender system based on trust and expert agents. It aims at improving the quality of the information exchanged among agents because communication will occur primarily with trusted sources in the hope to decrease the communication load. Also, agents become experts in specific types of recommendation. The approach was validate in the tourism domain by means of recommendations of travel packages and experiments were performed to illustrate the impact of using trust assignment in the quality of the recommendations generated by expert agents. Results corroborate the intuition that expert agents that use a trust mechanism are able to increase the quality of recommendation provided.

Using Scientific Publications to Identify People with Similar Interests

In many situations, related to some types of systems or organizations’ tasks, it is necessary to identify people with similar profiles. In the case of a collaborative recommender system, items to be recommended are those associated to similar users. Another example, in the academic environment, is to identify new members to be part of a research group (people with similar profiles). This task of identifying people with similar profiles can be time-consuming. In this sense, this work considers that scientific papers written by people can be used to identify users with similar profiles. Considering this assumption, we have done some experiments to identify which parts of papers, which type of indexes (terms or concepts) and which type of similarity functions (Jaccard or a Fuzzy function) are more suitable to identify similar people. The paper presents the results of some experiments and some application scenarios considering academic environments.