The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study

Social media moderation policies are often at the center of public debate, and their implementation and enactment are sometimes surrounded by a veil of mystery. Unsurprisingly, due to limited platform transparency and data access, rela-tively little research has been devoted to characterizing mod- eration dynamics, especially in the context of controversial events and the platform activity associated with them. Here, we study the dynamics of account creation and suspension on Twitter during two global political events: Russia’s invasion of Ukraine and the 2022 French Presidential election. Leveraging a large-scale dataset of 270M tweets shared by 16M users in multiple languages over several months, we identify peaks of suspicious account creation and suspension, and we characterize behaviours that more frequently lead to account suspension. We show how large numbers of accounts get sus- pended within days from their creation. Suspended accounts tend to mostly interact with legitimate users, as opposed to other suspicious accounts, often making unwarranted and excessive use of reply and mention features, and predominantly sharing spam and harmful content. While we are only able to speculate about the speciﬁc causes leading to a given account suspension, our ﬁndings shed light on patterns of platform abuse and subsequent moderation during major events.

How Does Twitter Account Moderation Work? Dynamics of Account Creation and Suspension During Major Geopolitical Events

/pdf/modularity-aware-graph-autoencoders-for-joint-community-2i4ik8wy.pdf

Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction

Political competitions are complex settings where candidates use campaigns to promote their chances to be elected. One choice focuses on conducting a positive campaign that highlights the candidate’s achievements, leadership skills, and future programs. The alternative is to focus on a negative campaign that emphasizes the negative aspects of the competing person and is aimed at offending opponents or the opponent’s supporters. In this proposal, we concentrate on negative campaigns in Israeli elections. This work introduces an empirical case study on automatic detection of negative campaigns, using machine learning and natural language processing approaches, applied to the Hebrew-language data from Israeli municipal elections. Our contribution is multi-fold: (1) We provide TONIC—daTaset fOr Negative polItical Campaign in Hebrew—which consists of annotated posts from Facebook related to Israeli municipal elections; (2) We introduce results of a case study, that explored several research questions. RQ1: Which classifier and representation perform best for this task? We employed several traditional classifiers which are known for their good performance in IR tasks and two pre-trained models based on BERT architecture; several standard representations were employed with traditional ML models. RQ2: Does a negative campaign always contain offensive language? Can a model, trained to detect offensive language, also detect negative campaigns? We are trying to answer this question by reporting results for the transfer learning from a dataset annotated with offensive language to our dataset.

Detection of Negative Campaign in Israeli Municipal Elections

Political competitions are complex settings where candidates use campaigns to promote their chances to be elected. As we can recently observe, some candidates choose to focus on a negative campaign that emphasizes the negative aspects of the competing person and is aimed at offending opponents or the opponent’s supporters . The big challenge in this area is the lack of annotated datasets for training efficient classifiers. Therefore, transfer learning from other relevant domains and other languages could be very useful for this task. Considering the recent success of meta-learning in domain adaptation, we apply it to our task of utilizing available datasets from different domains and languages. This work explores the negative campaign detection task from multiple perspectives: the efficiency of different text representations and classification models, and the effect of transfer learning from offensive language detection in different languages for negative campaign detection in Hebrew. We demonstrate that the lack of training data for negative campaign detection in a low-resourced language such as Hebrew can be compensated to some extent by available datasets for offensive language detection in the same and other languages. We report an empirical case study for political campaigns in Israeli municipal elections. 1

Cross-lingual Transfer Learning for Detecting Negative Campaign in Israeli Municipal Elections: a Case Study

We introduce BERTweetFR, the first large-scale pre-trained language model for French tweets. Our model is initialized using the general-domain French language model CamemBERT which follows the base architecture of RoBERTa. Experiments show that BERTweetFR outperforms all previous general-domain French language models on two downstream Twitter NLP tasks of offensiveness identification and named entity recognition. The dataset used in the offensiveness detection task is first created and annotated by our team, filling in the gap of such analytic datasets in French. We make our model publicly available in the transformers library with the aim of promoting future research in analytic tasks for French tweets.

BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets

With the significant increase in users on social media platforms, a new means of political campaigning has appeared. Twitter and Facebook are now notable campaigning tools during elections. Indeed, the candidates and their parties now take to the internet to interact and spread their ideas. In this paper, we aim to identify political communities formed on Twitter during the 2022 French presidential election and analyze each respective community. We create a large-scale Twitter dataset containing 1.2 million users and 62.6 million tweets that mention keywords relevant to the election. We perform community detection on a retweet graph of users and propose an in-depth analysis of the stance of each community. Finally, we attempt to detect offensive tweets and automatic bots, comparing across communities in order to gain insight into each candidate’s supporter demographics and online campaign strategy.

Political Communities on Twitter: Case Study of the 2022 French Presidential Election

Graphs evolved as very effective representations of different types of data including social networks, biological data or textual documents. In the past years, significant efforts have been devoted to methods that learn vector representations of nodes or of entire graphs. But edges, representing interactions between nodes, have attracted less attention. Surprisingly, there are only a few studies that focus on generating edge representations or deal with edge-related tasks such as the problem of edge classification. In this paper, we propose a new model (in the form of an auto-encoder) to learn edge embeddings in (un)directed graphs. The encoder corresponds to a graph neural network followed by an aggregation function, while a multi-layer perceptron serves as our decoder. We empirically evaluate our approach in two different tasks, namely edge classification and link prediction. In the first task, the proposed model outperforms the baselines, while in the second task, it achieves results that are comparable to the state-of-the-art.

Graph Auto-Encoders for Learning Edge Representations

A system that could reliably identify and sum up the most important points of a conversation would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls. Recent advances in deep learning, and especially the invention of encoder-decoder architectures, has significantly improved language generation systems, opening the door to improved forms of abstractive summarization, a form of summarization particularly well-suited for multi-party conversation. In this paper, we provide an overview of the challenges raised by the task of abstractive meeting summarization and of the data sets, models and evaluation metrics that have been used to tackle the problems.

Abstractive Meeting Summarization: A Survey

We introduce BERTweetFR, the first large-scale pre-trained language model for French tweets. Our model is initialised using a general-domain French language model CamemBERT which follows the base architecture of BERT. Experiments show that BERTweetFR outperforms all previous general-domain French language models on two downstream Twitter NLP tasks of offensiveness identification and named entity recognition. The dataset used in the offensiveness detection task is first created and annotated by our team, filling in the gap of such analytic datasets in French. We make our model publicly available in the transformers library with the aim of promoting future research in analytic tasks for French tweets.

Virgile Rennard

Papers

BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets

Political Communities on Twitter: Case Study of the 2022 French Presidential Election

Graph Auto-Encoders for Learning Edge Representations

Abstractive Meeting Summarization: A Survey

BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets