91 research outputs found
Motion detection technology as a tool for cardiopulmonary resuscitation (CPR) quality improvement
No full textThe most popular method of training in basic life support and AED remains instructor-led training courses. Recent reviews provide good evidence to support alternative methods of training including lay instructors, self-directed learning (web, video, poster) and CPR feedback/prompt devices
FakeNewsLab: Experimental Study on Biases and Pitfalls Preventing us from Distinguishing True from False News
No full textMisinformation posting and spreading in Social Media is ignited by personal
decisions on the truthfulness of news that may cause wide and deep cascades at
a large scale in a fraction of minutes. When individuals are exposed to
information, they usually take a few seconds to decide if the content (or the
source) is reliable, and eventually to share it. Although the opportunity to
verify the rumour is often just one click away, many users fail to make a
correct evaluation. We studied this phenomenon with a web-based questionnaire
that was compiled by 7,298 different volunteers, where the participants were
asked to mark 20 news as true or false. Interestingly, false news is correctly
identified more frequently than true news, but showing the full article instead
of just the title, surprisingly, does not increase general accuracy. Also,
displaying the original source of the news may contribute to mislead the user
in some cases, while a genuine wisdom of the crowd can positively assist
individuals' ability to classify correctly. Finally, participants whose
browsing activity suggests a parallel fact-checking activity, show better
performance and declare themselves as young adults. This work highlights a
series of pitfalls that can influence human annotators when building false news
datasets, which in turn fuel the research on the automated fake news detection;
furthermore, these findings challenge the common rationale of AI that suggest
users to read the full article before re-sharing.Comment: 18 pages, 12 figures, 3 table
Analyzing and visualizing polarization and balance with signed networks: the U.S. Congress case study
No full textSigned networks and balance theory provide a natural setting for real-world
scenarios that show polarization dynamics, positive/negative relationships, and
political partisanship. For example, they have been proven effective in
studying the increasing polarization of the votes in the two chambers of the
U.S. Congress from World War II on.
To provide further insights into this particular case study, we propose the
application of a pipeline to analyze and visualize a signed graph's
configuration based on the exploitation of the corresponding Laplacian matrix'
spectral properties. The overall methodology is comparable with others based on
the frustration index, but it has at least two main advantages: first, it
requires a much lower computational cost; second, it allows for a quantitative
and visual assessment of how arbitrarily small subgraphs (even single nodes)
contribute to the overall balance (or unbalance) of the network.
The proposed pipeline allows the exploration of polarization dynamics shown
by the U.S. Congress from 1945 to 2020 at different resolution scales. In fact,
we are able to spot and point out the influence of some (groups of) congressmen
in the overall balance, as well as to observe and explore polarization's
evolution of both chambers across the years
Writing about COVID-19 vaccines: Emotional profiling unravels how mainstream and alternative press framed AstraZeneca, Pfizer and vaccination campaigns
No full textSince their announcement in November 2020, COVID-19 vaccines were largely
debated by the press and social media. With most studies focusing on COVID-19
disinformation in social media, little attention has been paid to how
mainstream news outlets framed COVID-19 narratives compared to alternative
sources. To fill this gap, we use cognitive network science and natural
language processing to reconstruct time-evolving semantic and emotional frames
of 5745 Italian news, that were massively re-shared on Facebook and Twitter,
about COVID-19 vaccines. We found consistently high levels of
trust/anticipation and less disgust in the way mainstream sources framed the
general idea of "vaccine/vaccino". These emotions were crucially missing in the
ways alternative sources framed COVID-19 vaccines. More differences were found
within specific instances of vaccines. Alternative news included titles framing
the AstraZeneca vaccine with strong levels of sadness, absent in mainstream
titles. Mainstream news initially framed "Pfizer" along more negative
associations with side effects than "AstraZeneca". With the temporary
suspension of the latter, on March 15th 2021, we identified a
semantic/emotional shift: Even mainstream article titles framed "AstraZeneca"
as semantically richer in negative associations with side effects, while
"Pfizer" underwent a positive shift in valence, mostly related to its higher
efficacy. "Thrombosis" entered the frame of vaccines together with fearful
conceptual associations, while "death" underwent an emotional shift, steering
towards fear in alternative titles and losing its hopeful connotation in
mainstream titles. Our findings expose crucial aspects of the emotional
narratives around COVID-19 vaccines adopted by the press, highlighting the need
to understand how alternative and mainstream media report vaccination news.Comment: 16 pages, 5 figure
The Impact of Disinformation on a Controversial Debate on Social Media
No full textIn this work we study how pervasive is the presence of disinformation in the
Italian debate around immigration on Twitter and the role of automated accounts
in the diffusion of such content. By characterising the Twitter users with an
\textit{Untrustworthiness} score, that tells us how frequently they engage with
disinformation content, we are able to see that such bad information
consumption habits are not equally distributed across the users; adopting a
network analysis approach, we can identify communities characterised by a very
high presence of users that frequently share content from unreliable news
sources. Within this context, social bots tend to inject in the network more
malicious content, that often remains confined in a limited number of clusters;
instead, they target reliable content in order to diversify their reach. The
evidence we gather suggests that, at least in this particular case study, there
is a strong interplay between social bots and users engaging with unreliable
content, influencing the diffusion of the latter across the network
Studying fake news spreading, polarisation dynamics, and manipulation by bots: A tale of networks and language
No full text[EN] With the explosive growth of online social media, the ancient problem of information disorders interfering with news diffusion has surfaced with a renewed intensity threatening our democracies, public health, and news outlets¿ credibility. Therefore, thousands of scientific papers have been published in a relatively short period, making researchers of different disciplines struggle with an information overload problem. The aim of this survey is threefold: (1) we present the results of a network-based analysis of the existing multidisciplinary literature to support the search for relevant trends and central publications; (2) we describe the main results and necessary background to attack the problem under a computational perspective; (3) we review selected contributions using network science as a unifying framework and computational linguistics as the tool to make sense of the shared content. Despite scholars working on computational linguistics and networks traditionally belong to different scientific communities, we expect that those interested in the area of fake news should be aware of crucial aspects of both disciplines.The work of Paolo Rosso was carried out in the framework of
the IBERIFIER hub on Iberian media research and factchecking funded by the European Digital Media Observatory
(INEA/CEF/ICT/A202072381931 n.2020-EU-IA-0252), and the following projects: XAI-Disinfodemics on eXplainable AI for
disinformation and conspiracy detection during infodemics
(PLEC2021-007681) and MARTINI on Malicious Actors pRofiling
and deTection In online social Networks through artificial Intelligence (PCI2022-134990-2) of the CHISTERA IV Cofund 2021
program, funded by MCIN/AEI/10.13039/501100011033, Spain
and by the European Union NextGenerationEU/PRTR, Spain .Ruffo, G.; Semeraro, A.; Giachanou, A.; Rosso, P. (2023). Studying Fake News Spreading, Polarisation Dynamics, and Manipulation by Bots: a Tale of Networks and Language. Computer Science Review. 47. https://doi.org/10.1016/j.cosrev.2022.100531S4
Structural inequalities emerging from a large wire transfers network
No full textWe aim to explore the connections between structural network inequalities and bank’s customer spending behaviours, within an entire national ecosystem made of natural persons (i.e., an individual human being) and legal entities (i.e., private or public organisations), different business sectors, and supply chains that span distinct geographical regions. We focus on Italy, that is among the wealthiest nations in the world, and also an example of a complex economic system. In particular, we had access to a large subset of anonymised and GDPR-compliant wire transfer data recorded from Jan 2016 to Dec 2017 by Intesa Sanpaolo, a leading banking group in the Eurozone, and the most important one in Italy.Intesa Sanpaolo wire transfers network exhibits a strong heavy-tailed behaviour and a giant component that grows continuously around the same core of the 1% highest degree nodes, and it also shows a general disassortative pattern, even if some ranges of degrees’ values stand out from the trend. Structural heterogeneity is explored further by means of a bow-tie analysis, that shows clearly that the majority of relevant, in terms of transferred amount, transactions is settled between a smaller set of nodes that are associated to legal entities and that mostly belong to the strongly connected component. This observation brings to a more comprehensive inspection of differences between Italian regions and business sectors, that could support the detection and the understanding of the interplay between supply chains.Our results suggest that there is a general flow of money that seems to stream down from higher degree legal entities to lower degree natural persons, crossing Italian regions and connecting different business sectors, and that is finally redistributed through expenses sharing within families and smaller communities. We also describe a reference dataset and an empirical contribution to the study on financial networks, focusing on finer-grained information concerned about spending behaviour through wire transfers
Contextualized BERT Sentence Embeddings for Author Profiling: The Cost of Performances
No full textThe necessity to know information about the real identity of an online subject is a highly relevant issue in User Profiling, especially for analysis from digital sources such as social media. The digital identity of a user does not always present explicit data about her offline life such as age, gender, work, and more. This problem makes the task of user profiling complex and incomplete. For many years this issue has received a considerable amount of attention from the whole community, which has developed several solutions, also based on machine learning, to estimate user characteristics. The increasing diffusion of deep learning approaches has allowed, on the one hand, to obtain a considerable increase in predictive performance, but on the other hand, to have available models that cannot be interpreted and that require very high computational power. Considering the validity of new pre-trained language models on extensive data for resolving many natural language processing and classification tasks, we decided to propose a BERT-based approach (BERT-DNN) also for the author profiling task. In a first analysis, we compared the results obtained by our model with them of more classical approaches. As a follow, a critical analysis was carried out. We analyze the advantages and disadvantages of these approaches also in terms of resources needed to run them. The results obtained by our model are encouraging in terms of reliability but very disappointing if we consider the computational power required for running it
EmoAtlas: An emotional network analyzer of texts that merges psychological lexicons, artificial intelligence, and network science
No full textWe introduce EmoAtlas, a computational library/framework extracting emotions and syntactic/semantic word associations from texts. EmoAtlas combines interpretable artificial intelligence (AI) for syntactic parsing in 18 languages and psychologically validated lexicons for detecting the eight emotions in Plutchik's theory. We show that EmoAtlas can match or surpass transformer-based natural language processing techniques, BERT or large language models like ChatGPT 3.5 or LLaMAntino, in detecting emotions from Italian and English online posts and news articles (e.g., achieving 85.6 % accuracy in detecting anger in posts vs the 68.8 % value of ChatGPT and 89.9% value for BERT). EmoAtlas presents important advantages in terms of speed and absence of fine-tuning, e.g., it runs 12x faster than BERT on the same data. Testing EmoAtlas' and easily trainable transformers' relevance in a psychometric task like reproducing human creativity ratings for 1071 short texts, we find that EmoAtlas and BERT obtain equivalent predictive power (fourfold cross-validation, ρ≈0.495 , p<10-4 ). Combining BERT's semantic features with EmoAtlas' emotional/syntactic networks of words gets substantially better at estimating creativity rates of stories ( ρ=0.628 , p<10-4 ). This indicates an interplay between the creativity of narratives and their semantic, emotional, and syntactic structure. Via interpretable emotional profiles and syntactic networks, EmoAtlas can also quantify how emotions are channeled through specific words in texts, e.g., how did customers frame their ideas and emotions towards "beds" in hotel reviews? We release EmoAtlas as a standalone "text as data" computational tool and discuss its impact in extracting interpretable and reproducible insights from texts
Intelligent Information Access
No full textIntelligent Information Access techniques attempt to overcome the limitations of current search devices by providing personalized information items
and product/service recommendations. They normally utilize direct or indirect
user input and facilitate the information search and decision processes,
according to user needs, preferences and usage patterns. Recent developments
at the intersection of Information Retrieval, Information Filtering,
Machine Learning, User Modelling, Natural Language Processing and Human-
Computer Interaction offer novel solutions that empower users to go beyond
single-session lookup tasks and that aim at serving the more complex requirement:
“Tell me what I don’t know that I need to know”. Information filtering
systems, specifically recommender systems, have been revolutionizing the way
information seekers find what they want, because they effectively prune large
information spaces and help users in selecting items that best meet their needs
and preferences. Recommender systems rely strongly on the use of various
machine learning tools and algorithms for learning how to rank, or predict
user evaluation, of items. Information Retrieval systems, on the other hand,
also attempt to address similar filtering and ranking problems for pieces of
information such as links, pages, and documents. But they generally focus
on the development of global retrieval techniques, often neglecting individual
user needs and preferences.
The book aims to investigate current developments and new insights into
methods, techniques and technologies for intelligent information access from
a multidisciplinary perspective. It comprises six chapters authored by participants
in the research event Intelligent Information Access, held in Cagliari
(Italy) in December 2008.
In Chapter 1, Enhancing Conversational Access to Information through a
Socially Intelligent Agent, Berardina De Carolis, Irene Mazzotta and Nicole
Novielli emphasize the role of Embodied Conversational Agents (ECAs) as
a natural interaction metaphor for personalized and context-adapted access
to information. They propose a scalable architecture for the development of
ECAs able to exhibit an emotional state and/or social signs.
VI Preface
The automatic detection of emotions in text is the problem investigated
in Chapter 2, Annotating and Identifying Emotions in Text, by Carlo Strapparava
and Rada Mihalcea. The authors describe the “Affective Text” task,
presented at SEMEVAL- 2007. The task focused on classifying emotions in
news headlines, and was intended to explore the connection between emotions
and lexical semantics. After illustrating the data set, the rationale of
the task and a brief description of the participating systems, several experiments
on the automatic annotation of emotions in text are presented. The
practical applications of the task are very important. Consider for example
opinion mining and market analysis, affective computing, natural language
interfaces for e-learning environments or educational games.
Personalization of the ranking computed by search engines and recommender
systems is the main topic of Chapter 3, Improving Ranking by Respecting
the Multidimensionality and Uncertainty of User Preferences, by
Bettina Berendt and Veit Koppen. The research question addressed by the
authors is whether system ranking is the “right ranking” for the user, based
on the context in which she/he operates. A general conceptualization of the
ranking-evaluation task is proposed: the comparison between the ranking
generated by a computational system, and the “ user’s ideal ranking”. Eight
challenges to this simple model are discussed, leading to the conclusion that
approaches for dealing with multidimensional, and often only partial, preference
orders are required and that randomness could be a beneficial feature
of system rankings.
In Chapter 4, Hotho reviews the state of the art in the new research area
of data mining on folksonomies. The first part describes the basics of folksonomies,
summarizing del.icio.us, the most popular social bookmarking system,
and illustrates in detail BibSonomy, a very successful online service for
social bookmarking and publication sharing. Starting from these systems,
the author discusses in greater depth the main issues regarding folksonomies,
proposing a formal model and presenting their most important network properties.
In the second part, the author illustrates three applications: spam
detection, ranking and recommendation. Regarding spam detection, the author
develops techniques, based on binary classifiers, which prevent spammers
from publishing in social bookmarking systems. As far as ranking is
concerned, a new algorithm is proposed, namely FolkRank, which takes into
account the folksonomy structure for ranking users, tags and resources. For
recommendation, the author evaluates a tag recommender based on Collaborative
Filtering, a graph based recommender using FolkRank and several
simple approaches based on tag counts. In the third part, a possible
link between folksonomies and ontologies is suggested, paving the way to
some very promising strategies for detecting organizational principles hidden
within folksonomies.
Amati, Amodeo, Bianchi, Gaibisso and Gambosi propose, in Chapter 5, A Uniform Theoretic Approach to Opinion and Information Retrieval,
an application of the Divergence From Randomness (DFR) model to the
Preface VII
opinion finding task, the task of retrieving opinionated blog posts, relevant for
a given topic, from a large collection. The opinion finding task can be seen as a
search in which, after the standard retrieval of ranked documents, documents
are re-ranked according to the presence of opinions within the selected documents.
This task can be handled by a supervised or unsupervised method.
The authors propose a method for creating a lexicon of opinionated terms
for re-ranking the documents, using a supervised algorithm. The first part
introduces the statistical basis underpinning the proposed approach and its
adoption in opinion retrieval. In particular, two information-theoretic functions
are defined, opinion entropy and average opinion entropy. The authors
also formally describe their lightweight opinion retrieval algorithm. Lastly, the
authors discuss the effectiveness of their approach for creating a dictionary
of polarity-bearing terms. They also describe some preliminary experiments
and propose alternative ways to approach the polarity detection problem.
In Chapter 6, A Suite of Semantic Web Tools Supporting Development
of Multilingual Ontologies, Pazienza, Stellato and Turbati propose a suite of
software libraries, tools and ontologies to support multilingual development
of Semantic Web ontologies. The three tools illustrated in this Chapter are
Semantic Turkey, The Linguistic Watermark, and Ontoling. Semantic Turkey
is aimed at providing innovative solutions for web browsing and for gathering
and organizing the information observed when surfing the net. The novel
aspect of Semantic Turkey is its ability to provide a clear separation between
acquired data and web links. The Linguistic Watermark is an ontological and
software framework for describing and managing heterogeneous linguistic resources
and for using their contents for ontological-driven document enrichment.
Ontoling is a generic architecture for extending ontology development
tools with functionalities for enriching ontological knowledge with linguistic
content. The tools presented implicitly embed a new way of rethinking the
development of ontologies in terms of making their content reusable and comprehensible.
Furthermore, they represent living proof of software engineering
principles associated with software reuse, documentation, modularity, interaction
analysis, applied to the domain of Knowledge Management Software.
We would like to thank all the authors for their excellent contributions and
the reviewers for their careful revision and suggestions for improving them.
We are grateful to the Springer-Verlag Team for their assistance during the
preparation of the manuscripts.
This book is dedicated to the memory of Fiorella de Rosis in recognition of
her contribution to user modeling. She was a pioneer in the field of affective
computing, a leader in research on modeling emotions and constructing embodied
animated agents. She produced key contributions in intelligent user
interfaces, in particular on user-adapted generation of natural language and
multimedia messages, uncertainty in user models, and presentation of medical
explanations and clinical guidelines. During her teaching and research activities
she mentored many students who have become established researchers.
These research and teaching activities didn’t prevent her from being an active
VIII Preface
member of the ACM, of the International Society for Research on Emotions,
of the European Network of Excellence on Emotions (HUMAINE), of the
editorial boards of UMUAI and co-chair of many international conferences.
All the people acquainted with Fiorella have appreciated her scientific and
human value and are grateful for her friendship
- …
