Fabio Clarizia

Mixed graph of terms for query expansion

It is well known that one way to improve the accuracy of a text retrieval system is to expand the original query with additional knowledge coded through topic-related terms. In the case of an interactive environment, the expansion, which is usually represented as a list of words, is extracted from documents whose relevance is known thanks to the feedback of the user. In this paper we argue that the accuracy of a text retrieval system can be improved if we employ a query expansion method based on a mixed Graph of Terms representation instead of a method based on a simple list of words. The graph, that is composed of a directed and an undirected subgraph, can be automatically extracted from a small set of only relevant documents (namely the user feedback) using a method for term extraction based on the probabilistic Topic Model. The evaluation of the proposed method has been carried out by performing a comparison with two less complex structures: one represented as a set of pairs of words and another that is a simple list of words.

An Adaptive Optimisation Method for Automatic Lightweight Ontology Extraction

It is well known how the use of additional knowledge, coded through ontologies, can improve the quality of the results obtained, in terms of user satisfaction, when seeking information on the web. The choice of a knowledge base, as long as it is reduced to small domains, is still manageable in a semi-automatic mode. However, in wider contexts, where a higher scalability is required, a fully automatic procedure is needed.

A Mobile Context-Aware Information System to Support Tourism Events

The experience of a touristic visit is a learning process very fascinating and interesting: the emotions can change according to the interests of the individuals, as well as of the physical, personal and social-cultural context. Applications for a mobile environment should take advantage of contextual information, such as position, to offer greater services to the user.

An Ontological Digital Storytelling to Enrich Tourist Destinations and Attractions with a Mobile Tailored Story.

Storytelling has evolved over the years: its ability to enchant, transform and persuade makes it a formidable mean, malleable and customizable, but not easy to use. The use of new technologies allowing it to reach a far greater level of effectiveness: the audience can join in the storytelling process, thus impacting positively on engagement and facilitating the development of long lasting relationships.

A new text classification technique using small training sets

Text classification methods have been evaluated on supervised classification tasks of large datasets showing high accuracy. Nevertheless, due to the fact that these classifiers, to obtain a good performance on a test set, need to learn from many examples, some difficulties may be found when they are employed in real contexts. In fact, most users of a practical system do not want to carry out labeling tasks for a long time only to obtain a better level of accuracy. They obviously prefer algorithms that have high accuracy, but do not require a large amount of manual labeling tasks. In this paper we propose a new supervised method for single-label text classification, based on a mixed Graph of Terms, that is capable of achieving a good performance, in term of accuracy, when the size of the training set is 1% of the original. The mixed Graph of Terms can be automatically extracted from a set of documents following a kind of term clustering technique weighted by the probabilistic topic model. The method has been tested on the top 10 classes of the ModApte split from the Reuters-21578 dataset and learned on 1% of the original training set. Results have confirmed the discriminative property of the graph and have confirmed that the proposed method is comparable with existing methods learned on the whole training set.

SEMANTIC INDEXING OF WEB PAGES VIA PROBABILISTIC METHODS - In Search of Semantics Project

In this paper we address the problem of modeling large collections of data, namely web pages by exploiting jointly traditional information retrieval techniques with probabilistic ones in order to find semantic descriptions for the collections. This novel technique is embedded in a real Web Search Engine in order to provide semantics functionalities, as prediction of words related to a single term query. Experiments on different small domains (web repositories) are presented and discussed.

E-learning and sentiment analysis: a case study

E-Learning is becoming one of the most effective training approaches. In particular, the blended learning is considered a useful methodology for supporting and understanding students and their learning issues. Thanks to e-Learning platforms and their collaborative tools, students can interact with other students and share doubts on certain topics. However, teachers often remain outside of this process and do not understand the learning problems that are in their classrooms. A solution for ensuring the privacy of communication among students could be the adoption of a Sentiment Analysis methodology for the detection of the classroom mood during the learning process. In this paper, we investigate the adoption of a probabilistic approach based on the Latent Dirichlet Allocation (LDA) as Sentiment Grabber. The proposed approach can detect the mood of students on the various topics and teacher can better tune his/her teaching approach. The proposed method has been tested in real cases with effective and satisfactory results.

A Probabilistic Method for Text Analysis

Textual materials are source of extremely valuable information, for which there must be a reflection on the techniques of analysis to be used to avoid subjective interpretations especially in the content. The Textual Analysis (TA), which makes use of statistical techniques, ensures the systematic exploration of the structure of the text (size, occurrence, etc.) and simultaneously the possibility to return at any time to the original text for the appropriate interpretations. In this work we test a new technique based on a probabilistic model of language known in the literature as “topic model” for analyzing corpora of documents about electromagnetic pollution. The proposed method is able to reveal how the meaning of a document is distributed all along its spectrum (word-frequency) indicating that the real meaning of a document can be inferred following a multilevel analysis. Such analysis is carried out exploiting a new concept of ontology already used in literature and deeply explained here.

A Multilevel Graph Approach for Road Accidents Data Interpretation

Nowadays, due to the massive low-cost technology and mobile devices spread, our society is increasingly projected towards data production. Often, we find ourselves surrounded by data that, however, does not always lead to the knowledge, or toward information that we need. This is liable to eclipse the desire to use this data trying to predict the future. So much has been done in literature in regard to the extraction of information and interpretation of these data. However, in this field does not seem to be present a universal methodology for solving the problem, leading us to research new approaches more customized on the available dataset. The aim of this paper is to introduce an approach for the interpretation of data from sensors located within a city using three graphical views: Context Dimension Tree, Ontologies and Bayesian Networks. Through the Ontologies and the Context Dimension Tree it is possible to analyze the scenario from a syntactic and semantic point of view, assisting the construction of the he Bayes network structure that allow to estimate the probability that some events happen. A first preliminary analysis conducted on a London borough seems to confirm the effectiveness of the proposed method.

Chatbot: An Education Support System for Student

In the last few years there has been a fast growing up of the use of Chatbots in various fields, such as Health Care, Marketing, Educational, Supporting Systems, Cultural Heritage, Entertainment and many others. This paper presents the realization of a prototype of a Chatbot in educational domain: the purpose has focused on the design of the specific architecture, model to manage communication and furnish the right answers to the student. For this aim, it has been realized a system that can detect the questions and thanks to the use of natural language processing techniques and the ontologies of domain, gives the answers to student. Finally, after the implementation of the designed model, experimental campaign was conducted in order to demonstrate its utility.