caterina senette

Dr. caterina senette

Institute of Informatics and Telematics - CNR Pisa Italy

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2017 in Universal Access in the Information Society
Verified
Journal Article
Closed access
PDF file
SASilvia Artoni
Silvia Artoni
LBluca bastiani
luca bastiani
Maria Claudia BuzziMaria Claudia Buzzi
Maria Claudia Buzzi
MBMarina Buzzi
Marina Buzzi
Olivia CurzioOlivia Curzio
Olivia Curzio
caterina senettecaterina senette
caterina senette

12 July 2020 in Brain Sciences
Verified
Journal Article
Open access
PDF file
Antonio NarzisiAntonio Narzisi
Antonio Narzisi
MBMariasole Bondioli
Mariasole Bondioli
FPFrancesca Pardossi
Francesca Pardossi
Lucia BilleciLucia Billeci
Lucia Billeci
Maria Claudia BuzziMaria Claudia Buzzi
Maria Claudia Buzzi
Susanna PelagattiSusanna Pelagatti
Susanna Pelagatti
Children with autism spectrum disorder (ASD) show worse oral health than their peers. Their access to health services is, at present, inadequate: few high-quality interventions have been designed and implemented to improve their care procedures so far. The purpose of this study is to describe an experience of dental care supported by Information and Communication Technologies (ICT), for children with ASD in a public health service. In our study, 59 children (mean age 9.9 years; SD = 5.43) participated in the MyDentist project. It integrates classic dental care techniques with new practices for desensitization and fear control, delivered through an enhanced customized ICT-based intervention aiming at familiarizing the child with ASD with the medical setting and procedures. Two questionnaires were filled out by parents to describe the acceptability of the MyDentist experience for their children. Significant results were shown from T0 (before initiating MyDentist) to T1 (after 6 months of the MyDentist experience) regarding improved oral hygiene and cooperation during dental treatments. Families positively assessed the use of ICT support. In conclusion, the project demonstrated acceptability by parents, suggesting that public health dental care and prevention can be successfully implemented without resorting to costly pharmacological interventions (with potential side effects), taking better care of children’s health.

9 May 2018 in Universal Access in the Information Society
Verified
Journal Article
Closed access
PDF file
Maria Claudia BuzziMaria Claudia Buzzi
Maria Claudia Buzzi
MBMarina Buzzi
Marina Buzzi
EPErico Perrone
Erico Perrone
caterina senettecaterina senette
caterina senette

28 September 2015
Verified
Conference Paper
Open access
PDF file
Maria Claudia BuzziMaria Claudia Buzzi
Maria Claudia Buzzi
MBMarina Buzzi
Marina Buzzi
BLBarbara Leporini
Barbara Leporini
caterina senettecaterina senette
caterina senette
Geometry is a traditionally difficult subject to teach to visually impaired subjects. This paper investigates tools to help blind children learn geometry. An accessible vibro-tactile-based android application has been designed to allow children to make freehand drawings and play with geometry, recognizing common geometric shapes or topological configurations. An initial usability test of the application, performed by a blind researcher, has revealed some limitations of the proposed approach that could soon be overcome thanks to current technological innovation in the mobile world.

6 September 2024 in Machine Learning
Verified
Journal Article
Open access
PDF file
MGMargherita Gambini
Margherita Gambini
caterina senettecaterina senette
caterina senette
TFTiziano Fagni
Tiziano Fagni
Maurizio TesconiMaurizio Tesconi
Maurizio Tesconi
Current stance detection methods employ topic-aligned data, resulting in many unexplored topics due to insufficient training samples. Large Language Models (LLMs) pre-trained on a vast amount of web data offer a viable solution when training data is unavailable. This work introduces Tweets2Stance - T2S, an unsupervised stance detection framework based on zero-shot classification, i.e. leveraging an LLM pre-trained on Natural Language Inference tasks. T2S detects a five-valued user’s stance on social-political statements by analyzing their X (Twitter) timeline. The Ground Truth of a user’s stance is obtained from Voting Advice Applications (VAAs). Through comprehensive experiments, a T2S’s optimal setting was identified for each election. Linguistic limitations related to the language model are further addressed by integrating state-of-the-art LLMs like GPT-4 and Mixtral into the T2S framework. The T2S framework’s generalization potential is demonstrated by measuring its performance (F1 and MAE scores) across nine datasets. These datasets were built by collecting tweets from competing parties’ Twitter accounts in nine political elections held in different countries from 2019 to 2021. The results, in terms of F1 and MAE scores, outperformed all baselines and approached the best scores for each election. This showcases the ability of T2S, particularly when combined with state-of-the-art LLMs, to generalize across different cultural-political contexts.

25 November 2018
Verified
Conference Paper
Open access
PDF file
caterina senettecaterina senette
caterina senette
Maria Claudia BuzziMaria Claudia Buzzi
Maria Claudia Buzzi
MPMaria Teresa Paratore
Maria Teresa Paratore
ATAmaury Trujillo
Amaury Trujillo