About
57
Publications
16,884
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,923
Citations
Publications
Publications (57)
The detection of sensitive content in large datasets is crucial for ensuring that shared and analysed data is free from harmful material. However, current moderation tools, such as external APIs, suffer from limitations in customisation, accuracy across diverse sensitive categories, and privacy concerns. Additionally, existing datasets and open-sou...
In the dynamic realm of social media, diverse topics are discussed daily, transcending linguistic boundaries. However, the complexities of understanding and categorising this content across various languages remain an important challenge with traditional techniques like topic modelling often struggling to accommodate this multilingual diversity. In...
The success of online social platforms hinges on their ability to predict and understand user behavior at scale. Here, we present data suggesting that context-aware modeling approaches may offer a holistic yet lightweight and potentially privacy-preserving representation of user engagement on online social platforms. Leveraging deep LSTM neural net...
Content moderators play a key role in keeping the conversation on social media healthy. While the high volume of content they need to judge represents a bottleneck to the moderation pipeline, no studies have explored how models could support them to make faster decisions. There is, by now, a vast body of research into detecting hate speech, sometim...
This paper introduces a large collection of time series data derived from Twitter, postprocessed using word embedding techniques, as well as specialized fine-tuned language models. This data comprises the past five years and captures changes in n-gram frequency, similarity, sentiment and topic distribution. The interface built on top of this data e...
Understanding the users' patterns of visiting various location categories can help online platforms improve content personalization and user experiences. Current literature on predicting future location categories of a user typically employs features that can be traced back to the user, such as spatial geo-coordinates and demographic identities. Mo...
Pictorial emojis and stickers are commonly used in online social networking to facilitate and aid communications. We delve into the use of Bitmoji stickers, a highly expressive form of pictorial communication using avatars resembling actual users. We collect a large-scale dataset of the metadata of 3 billion Bitmoji stickers shared among 300 millio...
Recent progress in language model pre-training has led to important improvements in Named Entity Recognition (NER). Nonetheless, this progress has been mainly tested in well-formatted documents such as news, Wikipedia, or scientific articles. In social media the landscape is different, in which it adds another layer of complexity due to its noisy a...
We propose MINT, a new Multilingual INTimacy analysis dataset covering 13,384 tweets in 10 languages including English, French, Spanish, Italian, Portuguese, Korean, Dutch, Chinese, Hindi, and Arabic. We benchmarked a list of popular multilingual pre-trained language models. The dataset is released along with the SemEval 2023 Task 9: Multilingual T...
Social media platforms host discussions about a wide variety of topics that arise everyday. Making sense of all the content and organising it into categories is an arduous task. A common way to deal with this issue is relying on topic modeling, but topics discovered using this technique are difficult to interpret and can differ from corpus to corpu...
Language evolves over time, and word meaning changes accordingly. This is especially true in social media, since its dynamic nature leads to faster semantic shifts, making it challenging for NLP models to deal with new content and trends. However, the number of datasets and models that specifically address the dynamic nature of these social platfor...
In this paper we present TweetNLP, an integrated platform for Natural Language Processing (NLP) in social media. TweetNLP supports a diverse set of NLP tasks, including generic focus areas such as sentiment analysis and named entity recognition, as well as social media-specific tasks such as emoji prediction and offensive language identification. T...
The environment we are in can affect our mood and behavior. One environmental factor is weather, which is linked to sentiment as expressed on social media. However, less is known about how integrating changes in weather, along with time and location contextual cues, can improve sentiment detection and understanding. In this paper, we explore the ef...
Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models' capacity to deal with future and out-of-...
Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduc...
Contextual embeddings derived from transformer-based neural language models have shown state-of-the-art performance for various tasks such as question answering, sentiment analysis, and textual similarity in recent years. Extensive work shows how accurately such models can represent abstract, semantic information present in text. In this expository...
Prediction bias in machine learning models refers to unintended model behaviors that discriminate against inputs mentioning or produced by certain groups; for example, hate speech classifiers predict more false positives for neutral text mentioning specific social groups. Mitigating bias for each task or domain is inefficient, as it requires repeti...
The experimental landscape in natural language processing for social media is too fragmented. Each year, new shared tasks and datasets are proposed, ranging from classics like sentiment analysis to irony detection or emoji prediction. Therefore, it is unclear what the current state of the art is, as there is no standardized evaluation protocol, nei...
Cross-lingual embeddings represent the meaning of words from different languages in the same vector space. Recent work has shown that it is possible to construct such representations by aligning independently learned monolingual embedding spaces, and that accurate alignments can be obtained even without external bilingual data. In this paper we exp...
Cross-lingual embeddings represent the meaning of words from different languages in the same vector space. Recent work has shown that it is possible to construct such representations by aligning independently learned monolingual embedding spaces, and that accurate alignments can be obtained even without external bilingual data. In this paper we exp...
Cross-lingual embeddings represent the meaning of words from different languages in the same vector space. Recent work has shown that it is possible to construct such representations by aligning independently learned monolingual embedding spaces, and that accurate alignments can be obtained even without external bilingual data. In this paper we exp...
English. The Italian Emoji Prediction task (ITAmoji) is proposed at EVALITA 2018 evaluation campaign for the first time, after the success of the twin Multilingual Emoji Prediction Task, organized in the context of SemEval-2018 in order to challenge the research community to automatically model the semantics of emojis in Twitter. Participants were...
Sentiment analysis in social media is a popular task attracting the interest of the research community, also in recent evaluation campaigns of natural language processing tasks in several languages. We report on our experience in the organization of SENTIPOLC (SENTIment POLarity Classification Task), a shared task on sentiment classification of Ita...
The frequent use of Emojis on social media platforms has created a new form of multimodal social interaction. Developing methods for the study and representation of emoji semantics helps to improve future multimodal communication systems. In this paper, we explore the usage and semantics of emojis over time. We compare emoji embeddings trained on a...
Emojis are small images that are commonly included in social media text messages. The combination of visual and textual content in the same message builds up a modern way of communication, that automatic systems are not used to deal with. In this paper we extend recent advances in emoji prediction by putting forward a multimodal approach that is ab...
EVALITA is a periodic evaluation campaign of Natural Language Processing (NLP) and speech tools for the Italian language. The general objective of EVALITA is to promote the development of language and speech technologies for the Italian language, providing a shared framework where different systems and approaches can be evaluated in a consistent ma...
Emojis are ideograms which are naturally combined with plain text to visually complement or condense the meaning of a message. Despite being widely used in social media, their underlying semantics have received little attention from a Natural Language Processing standpoint. In this paper, we investigate the relation between words and emojis, studyi...
Choosing the right emoji to visually complement or condense the meaning of a message has become part of our daily life. Emojis are pictures, which are naturally combined with plain text, thus creating a new form of language. These pictures are the same independently of where we live, but they can be interpreted and used in different ways. In this p...
Emojis allow us to describe objects, situations and even feelings with small images, providing a visual and quick way to communicate. In this paper, we analyse emojis used in Twitter with distributional semantic models. We retrieve 10 millions tweets posted by USA users, and we build several skip gram word embedding models by mapping in the same ve...
EVALITA is the evaluation campaign of Natural Language Processing and Speech Tools for the Italian language: since 2007 shared tasks have been proposed covering the analysis of both written and spoken language with the aim of enhancing the development and dissemination of resources and technologies for Italian. EVALITA is an initiative of the Itali...
In this paper we present our approach to automatically identify the subjectivity, polarity and irony of Italian Tweets. Our system which reaches and outperforms the state of the art in Italian is well adapted for different domains since it uses abstract word features instead of bag of words. We also present experiments carried out to study how Ital...
Computational approaches to analyze figurative language are attracting a growing interest in Computational Linguistics. In this paper, we study the characterization of Twitter messages in Spanish that advertise satirical news. We present and evaluate a system able to classify tweets as satirical or not. To this purpose, we concentrate on the tweets...
In this article we present a Web-based demonstration of on-line text summarization and information extraction technology. News summarization in Spanish has been implemented in a system that monitors a news provider and summarizes the latest published news. The possibility to generate summaries from user's provided text is also available for English...
During the last few years, the investigation of methodologies to automatically detect and charac-terise the figurative traits of textual contents has attracted a growing interest. Indeed, the capability to correctly deal with figurative language and more specifically with satire is fundamental to build robust approaches in several sub-fields of Art...
In this paper, we describe the approach used by the UPF-taln team for tasks 10 and 11 of SemEval 2015 that respectively focused on “Sentiment Analysis in Twitter” and “Sentiment Analysis of Figurative Language in Twitter”. Our approach achieved satisfactory results in the figurative language analysis task, obtaining the second best result. In task...
We describe our participation to the SENTIPOLC task of EVALITA 2014. We experimented the use of intrinsic word features to characterise each Tweet. We relied only on these features to train a set of Decision Trees to characterise the subjectivity, the polarity and the ironic contents of each Tweet. In Task 1 and Task 2 our model shows good performa...
Irony is a linguistic device used to say something but meaning something else. The distinctive trait of ironic utterances is the opposition of literal and intended meaning. This characteristic makes the automatic recognition of irony a challenging task for current systems. In this paper we present and evaluate the first automated system targeted to...
Automatic detection of figurative language is a challenging task in computational lin-guistics. Recognising both literal and fig-urative meaning is not trivial for a ma-chine and in some cases it is hard even for humans. For this reason novel and accurate systems able to recognise figura-tive languages are necessary. We present in this paper a nove...
