Silvia N. Schiaffino

eTeacher: Providing personalized assistance to e-learning students

In this paper we present eTeacher, an intelligent agent that provides personalized assistance to e-learning students. eTeacher observes a students behavior while he/she is taking online courses and automatically builds the students profile. This profile comprises the students learning style and information about the students performance, such as exercises done, topics studied, exam results. In our approach, a students learning style is automatically detected from the students actions in an e-learning system using Bayesian networks. Then, eTeacher uses the information contained in the student profile to proactively assist the student by suggesting him/her personalized courses of action that will help him/her during the learning process. eTeacher has been evaluated when assisting System Engineering students and the results obtained thus far are promising.

Intelligent user profiling

User profiles or user models are vital in many areas in which it is essential to obtain knowledge about users of software applications. Examples of these areas are intelligent agents, adaptive systems, intelligent tutoring systems, recommender systems, intelligent e-commerce applications, and knowledge management systems. In this chapter we study the main issues regarding user profiles from the perspectives of these research fields. We examine what information constitutes a user profile; how the user profile is represented; how the user profile is acquired and built; and how the profile information is used. We also discuss some challenges and future trends in the intelligent user profiling area.

User - interface agent interaction: personalization issues

Interface agents are computer programs that provide personalized assistance to users with their computer-based tasks. Most interface agents achieve personalization by learning a users preferences in a given application domain and assisting him according to them. In this work we adopt a different approach to personalization: how to personalize the interaction between interface agents and users in a mixed-initiative interaction context. We have empirically studied a set of interaction issues that agents have to take into account to achieve this goal and we present our results in this article. Some of these personalization issues are: discovering the type of assistant a user wants, learning when (and if) to interrupt the user, discovering how the user wants to be assisted in different contexts. As a result of our experiments, we have defined the components of a user interaction profile that models a users interaction and assistance preferences. This profile will enable interface agents to enhance and personalize their interaction with users by discovering how to provide each user assistance of the right sort at the right time.

Entertainment recommender systems for group of users

Abstract Recommender systems are used to recommend potentially interesting items to users in different domains. Nowadays, there is a wide range of domains in which there is a need to offer recommendations to group of users instead of individual users. As a consequence, there is also a need to address the preferences of individual members of a group of users so as to provide suggestions for groups as a whole. Group recommender systems present a whole set of new challenges within the field of recommender systems. In this article, we present two expert recommender systems that suggest entertainment to groups of users. These systems, jMusicGroupRecommender and jMoviesGroupRecommender, suggest music and movies and utilize different methods for the generation of group recommendations: merging recommendations made for individuals, aggregation of individuals’ ratings, and construction of group preference models. We also describe the results obtained when comparing different group recommendation techniques in both domains.

Social influence in group recommender systems

Purpose – The purpose of this paper is to propose an approach to generate recommendations for groups on the basis of social factors extracted from a social network. Group recommendation techniques traditionally assumed users were independent individuals, ignoring the effects of social interaction and relationships among users. In this work the authors analyse the social factors available in social networks in the light of sociological theories which endorse individuals’ susceptibility to influence within a group. Design/methodology/approach – The approach proposed is based on the creation of a group model in two stages: identifying the items that are representative of the majoritys preferences, and analysing members’ similarity; and extracting potential influence from members’ interactions in a social network to predict a groups opinion on each item. Findings – The promising results obtained when evaluating the approach in the movie domain suggest that individual opinions tend to be accommodated to grou...

Personalized e-Learning Environments: Considering Students' Contexts *

Personalization in e-learning systems is vital since they are used by a wide variety of students with different characteristics. There are several approaches that aim at personalizing e-learning environments. However, they focus mainly on technological and/or networking aspects without caring of contextual aspects. They consider only a limited version of context while providing personalization. In our work, the objective is to improve e-learning environment personalization making use of a better understanding and modeling of the user’s educational and technological context using ontologies. We show an example of the use of our proposal in the AdaptWeb system, in which content and navigation recommendations are provided depending on the student’s context.

Persisting big-data: The NoSQL landscape

Abstract The growing popularity of massively accessed Web applications that store and analyze large amounts of data, being Facebook, Twitter and Google Search some prominent examples of such applications, have posed new requirements that greatly challenge traditional RDBMS. In response to this reality, a new way of creating and manipulating data stores, known as NoSQL databases, has arisen. This paper reviews implementations of NoSQL databases in order to provide an understanding of current tools and their uses. First, NoSQL databases are compared with traditional RDBMS and important concepts are explained. Only databases allowing to persist data and distribute them along different computing nodes are within the scope of this review. Moreover, NoSQL databases are divided into different types: Key-Value, Wide-Column, Document-oriented and Graph-oriented. In each case, a comparison of available databases is carried out based on their most important features.

Assisting students with argumentation plans when solving problems in CSCL

In CSCL systems, students who are solving problems in group have to negotiate with each other by exchanging proposals and arguments in order to resolve the conflicts and generate a shared solution. In this context, argument construction assistance is necessary to facilitate reaching to a consensus. This assistance is usually provided with isolated arguments by demand, but this does not offer students a real and integral view of the conflicts. In this work, we study the utilisation of argumentation plans to assist a student during the argumentation. The actions of an argumentation plan represent the arguments that a student might use during the argumentation process. Moreover, these plans can be integrated with the tasks needed to reach a shared solution. These plans give the student an integral and intuitive view of the problem resolution and the conflict that must be resolved. We evaluated our proposal with students of an Artificial Intelligence course. This evaluation was carried out by comparing three different assistance scenarios in which students had to solve exercises: no assistance, assistance with isolated arguments, and assistance with argumentation plans. The results obtained show that reaching consensus was easier for the students when the assistance was provided using argumentations plans.

Social group recommendation in the tourism domain

Recommender Systems learn users’ preferences and tastes in different domains to suggest potentially interesting items to users. Group Recommender Systems generate recommendations that intend to satisfy a group of users as a whole, instead of individual users. In this article, we present a social based approach for recommender systems in the tourism domain, which builds a group profile by analyzing not only users’ preferences, but also the social relationships between members of a group. This aspect is a hot research topic in the recommender systems area. In addition, to generate the individual and group recommendations our approach uses a hybrid technique that combines three well-known filtering techniques: collaborative, content-based and demographic filtering. In this way, the disadvantages of one technique are overcome by the others. Our approach was materialized in a recommender system named Hermes, which suggests tourist attractions to both individuals and groups of users. We have obtained promising results when comparing our approach with classic approaches to generate recommendations to individual users and groups. These results suggest that considering the type of users’ relationship to provide recommendations to groups leads to more accurate recommendations in the tourism domain. These findings can be helpful for recommender systems developers and for researchers in this area.

An architecture and platform for developing distributed recommendation algorithms on large-scale social networks

The creation of new and better recommendation algorithms for social networks is currently receiving much attention owing to the increasing need for new tools to assist users. The volume of available social data as well as experimental datasets force recommendation algorithms to scale to many computers. Given that social networks can be modelled as graphs, a distributed graph-oriented support able to exploit computer clusters arises as a necessity. In this work, we propose an architecture, called Lightweight-Massive Graph Processing Architecture, which simplifies the design of graph-based recommendation algorithms on clusters of computers, and a Java implementation for this architecture composed of two parts: Graphly, an API offering operations to access graphs; and jLiME, a framework that supports the distribution of algorithm code and graph data. The motivation behind the creation of this architecture is to allow users to define recommendation algorithms through the API and then customize their execution using job distribution strategies, without modifying the original algorithm. Thus, algorithms can be programmed and evaluated without the burden of thinking about distribution and parallel concerns, while still supporting environment-level tuning of the distributed execution. To validate the proposal, the current implementation of the architecture was tested using a followee recommendation algorithm for Twitter as case study. These experiments illustrate the graph API, quantitatively evaluate different job distribution strategies w.r.t. recommendation time and resource usage, and demonstrate the importance of providing non-invasive tuning for recommendation algorithms.