Virginie Zampa

Latent Semantic Analysis for User Modeling

Latent semantic analysis (LSA) is a tool for extracting semantic information from texts as well as a model of language learning based on the exposure to texts. We rely on LSA to represent the student model in a tutoring system. Domain examples and student productions are represented in a high-dimensional semantic space, automatically built from a statistical analysis of the co-occurrences of their lexemes. We also designed tutoring strategies to automatically detect lexeme misunderstandings and to select among the various examples of a domain the one which is best to expose the student to. Two systems are presented: the first one successively presents texts to be read by the student, selecting the next one according to the comprehension of the prior ones by the student. The second plays a board game (kalah) with the student in such a way that the next configuration of the board is supposed to be the most appropriate with respect to the semantic structure of the domain and the previous students moves.

Helping Students Understand Courses through Written Syntheses: An LSA-Based Online Advisor

In a life-long learning context, learners have to perform a lot of writing-based activities, like doc¬ument analysis, that are seldom assessed by teachers or tutors because this assessment is time-consuming. We introduce a service, Pensum, integrated in a PLE that helps students to understand a course content through writing a synthesis, as well as teachers and tutors to manage this activity. Based on natural language processing techniques, Pensum proposes just-in-time and reflexive feedback on a complex writing task.

On the design of a word game to enhance Italian language learning

The use of game-based apps in e-learning has become a relevant trend with the diffusion of smart mobile devices. This is particularly true in language learning, where new captivating word games become a mean to enlarge vocabulary and improve the lexical accuracy of the user. This work presents MagicWord, a game based on widely known game mechanisms, but specifically designed and developed in order to support beginners learning Italian through an A1 level e-learning course. The paper presents the design and implementation of a demo version of MagicWord, through the main challenges encountered during its creation.

PtiClic et PtiClic-Kids : jeux avec les mots permettant une acquisition lexicale par le joueur et par la machine

Cet article presente deux jeux lexicaux qui permettent a l’utilisateur d’acquerir ou de consolider des connaissances sur les mots, et a la machine de construire une ontologie generaliste. PtiClic et PtiClic-Kids se fondent sur deux methodes d’acquisition lexicale, a savoir l’Analyse Semantique Latente (LSA) et JeuxDeMots (JDM). Nous presenterons d’abord ces deux methodes. Nous exposerons ensuite l’interet a combiner ces deux methodes afin de combler les lacunes de chacune au travers de ces deux jeux. Enfin, nous detaillerons ces jeux, c’est-a-dire le public vise, les differences, etc. Nous expliquerons comment ils permettent une double acquisition : de vocabulaire par les utilisateurs et lexicale par la machine. Ceci a donc un interet a la fois en TICE et en TALN. Quant aux donnees recueillies, elles peuvent conduire a la constitution d’un lexique lie a l’âge d’acquisition des mots et des relations entre mots, dont de multiples applications, comme la correction ou la generation de textes, peuvent tirer profit.