arXiv subjects

Kareem Darwish

Publications and source records attributed to Kareem Darwish.

At least 37 records · Page 2Linked to original sources

arXiv2021

Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms

With the outbreak of the COVID-19 pandemic, people turned to social media to read and to share timely information including statistics, warnings, advice, and inspirational stories. Unfortunately, alongside all this useful information, there was also a new blending of medical and political misinformation and disinformation, which gave rise to the first global infodemic. While fighting this infodemic is typically thought of in terms of factuality, the problem is much broader as malicious content includes not only fake news, rumors, and conspiracy theories, but also promotion of fake cures, panic, racism, xenophobia, and mistrust in the authorities, among others. This is a complex problem that needs a holistic approach combining the perspectives of journalists, fact-checkers, policymakers, government entities, social media platforms, and society as a whole. Taking them into account we define an annotation schema and detailed annotation instructions, which reflect these perspectives. We performed initial annotations using this schema, and our initial experiments demonstrated sizable improvements over the baselines. Now, we issue a call to arms to the research community and beyond to join the fight by supporting our crowdsourcing annotation efforts.

cs.IR↗

arXiv2021

Arabic Offensive Language on Twitter: Analysis and Experiments

Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a dataset that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers use offensive language. Lastly, we conduct many experiments to produce strong results (F1 = 83.2) on the dataset using SOTA techniques.

cs.CL↗

arXiv2021

Pre-Training BERT on Arabic Tweets: Practical Considerations

Pretraining Bidirectional Encoder Representations from Transformers (BERT) for downstream NLP tasks is a non-trival task. We pretrained 5 BERT models that differ in the size of their training sets, mixture of formal and informal Arabic, and linguistic preprocessing. All are intended to support Arabic dialects and social media. The experiments highlight the centrality of data diversity and the efficacy of linguistically aware segmentation. They also highlight that more data or more training step do not necessitate better models. Our new models achieve new state-of-the-art results on several downstream tasks. The resulting models are released to the community under the name QARiB.

cs.CL↗

arXiv2021

BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets

During the last two decades, we have progressively turned to the Internet and social media to find news, entertain conversations and share opinion. Recently, OpenAI has developed a ma-chine learning system called GPT-2 for Generative Pre-trained Transformer-2, which can pro-duce deepfake texts. It can generate blocks of text based on brief writing prompts that look like they were written by humans, facilitating the spread false or auto-generated text. In line with this progress, and in order to counteract potential dangers, several methods have been pro-posed for detecting text written by these language models. In this paper, we propose a transfer learning based model that will be able to detect if an Arabic sentence is written by humans or automatically generated by bots. Our dataset is based on tweets from a previous work, which we have crawled and extended using the Twitter API. We used GPT2-Small-Arabic to generate fake Arabic Sentences. For evaluation, we compared different recurrent neural network (RNN) word embeddings based baseline models, namely: LSTM, BI-LSTM, GRU and BI-GRU, with a transformer-based model. Our new transfer-learning model has obtained an accuracy up to 98%. To the best of our knowledge, this work is the first study where ARABERT and GPT2 were combined to detect and classify the Arabic auto-generated texts.

cs.CL↗

arXiv2020

Political Framing: US COVID19 Blame Game

Through the use of Twitter, framing has become a prominent presidential campaign tool for politically active users. Framing is used to influence thoughts by evoking a particular perspective on an event. In this paper, we show that the COVID19 pandemic rather than being viewed as a public health issue, political rhetoric surrounding it is mostly shaped through a blame frame (blame Trump, China, or conspiracies) and a support frame (support candidates) backing the agenda of Republican and Democratic users in the lead up to the 2020 presidential campaign. We elucidate the divergences between supporters of both parties on Twitter via the use of frames. Additionally, we show how framing is used to positively or negatively reinforce users' thoughts. We look at how Twitter can efficiently be used to identify frames for topics through a reproducible pipeline.

cs.SI↗

arXiv2020

Unsupervised User Stance Detection on Twitter

We present a highly effective unsupervised framework for detecting the stance of prolific Twitter users with respect to controversial topics. In particular, we use dimensionality reduction to project users onto a low-dimensional space, followed by clustering, which allows us to find core users that are representative of the different stances. Our framework has three major advantages over pre-existing methods, which are based on supervised or semi-supervised classification. First, we do not require any prior labeling of users: instead, we create clusters, which are much easier to label manually afterwards, e.g., in a matter of seconds or minutes instead of hours. Second, there is no need for domain- or topic-level knowledge either to specify the relevant stances (labels) or to conduct the actual labeling. Third, our framework is robust in the face of data skewness, e.g., when some users or some stances have greater representation in the data. We experiment with different combinations of user similarity features, dataset sizes, dimensionality reduction methods, and clustering algorithms to ascertain the most effective and most computationally efficient combinations across three different datasets (in English and Turkish). We further verified our results on additional tweet sets covering six different controversial topics. Our best combination in terms of effectiveness and efficiency uses retweeted accounts as features, UMAP for dimensionality reduction, and Mean Shift for clustering, and yields a small number of high-quality user clusters, typically just 2--3, with more than 98\% purity. The resulting user clusters can be used to train downstream classifiers. Moreover, our framework is robust to variations in the hyper-parameter values and also with respect to random initialization.

cs.SI↗

arXiv2020

Predicting the Topical Stance of Media and Popular Twitter Users

Discovering the stances of media outlets and influential people on current, debatable topics is important for social statisticians and policy makers. Many supervised solutions exist for determining viewpoints, but manually annotating training data is costly. In this paper, we propose a cascaded method that uses unsupervised learning to ascertain the stance of Twitter users with respect to a polarizing topic by leveraging their retweet behavior; then, it uses supervised learning based on user labels to characterize both the general political leaning of online media and of popular Twitter users, as well as their stance with respect to the target polarizing topic. We evaluate the model by comparing its predictions to gold labels from the Media Bias/Fact Check website, achieving 82.6% accuracy.

cs.SI↗

arXiv2020

Arabic Dialect Identification in the Wild

We present QADI, an automatically collected dataset of tweets belonging to a wide range of country-level Arabic dialects -covering 18 different countries in the Middle East and North Africa region. Our method for building this dataset relies on applying multiple filters to identify users who belong to different countries based on their account descriptions and to eliminate tweets that are either written in Modern Standard Arabic or contain inappropriate language. The resultant dataset contains 540k tweets from 2,525 users who are evenly distributed across 18 Arab countries. Using intrinsic evaluation, we show that the labels of a set of randomly selected tweets are 91.5% accurate. For extrinsic evaluation, we are able to build effective country-level dialect identification on tweets with a macro-averaged F1-score of 60.6% across 18 classes.

cs.CL↗

arXiv2020

A Few Topical Tweets are Enough for Effective User-Level Stance Detection

Stance detection entails ascertaining the position of a user towards a target, such as an entity, topic, or claim. Recent work that employs unsupervised classification has shown that performing stance detection on vocal Twitter users, who have many tweets on a target, can yield very high accuracy (+98%). However, such methods perform poorly or fail completely for less vocal users, who may have authored only a few tweets about a target. In this paper, we tackle stance detection for such users using two approaches. In the first approach, we improve user-level stance detection by representing tweets using contextualized embeddings, which capture latent meanings of words in context. We show that this approach outperforms two strong baselines and achieves 89.6% accuracy and 91.3% macro F-measure on eight controversial topics. In the second approach, we expand the tweets of a given user using their Twitter timeline tweets, and then we perform unsupervised classification of the user, which entails clustering a user with other users in the training set. This approach achieves 95.6% accuracy and 93.1% macro F-measure.

cs.SI↗

arXiv2020

Arabic Diacritic Recovery Using a Feature-Rich biLSTM Model

Diacritics (short vowels) are typically omitted when writing Arabic text, and readers have to reintroduce them to correctly pronounce words. There are two types of Arabic diacritics: the first are core-word diacritics (CW), which specify the lexical selection, and the second are case endings (CE), which typically appear at the end of the word stem and generally specify their syntactic roles. Recovering CEs is relatively harder than recovering core-word diacritics due to inter-word dependencies, which are often distant. In this paper, we use a feature-rich recurrent neural network model that uses a variety of linguistic and surface-level features to recover both core word diacritics and case endings. Our model surpasses all previous state-of-the-art systems with a CW error rate (CWER) of 2.86\% and a CE error rate (CEER) of 3.7% for Modern Standard Arabic (MSA) and CWER of 2.2% and CEER of 2.5% for Classical Arabic (CA). When combining diacritized word cores with case endings, the resultant word error rate is 6.0% and 4.3% for MSA and CA respectively. This highlights the effectiveness of feature engineering for such deep neural models.

cs.CL↗

arXiv2020

Quantifying Polarization on Twitter: the Kavanaugh Nomination

This paper addresses polarization quantification, particularly as it pertains to the nomination of Brett Kavanaugh to the US Supreme Court and his subsequent confirmation with the narrowest margin since 1881. Republican (GOP) and Democratic (DNC) senators voted overwhelmingly along party lines. In this paper, we examine political polarization concerning the nomination among Twitter users. To do so, we accurately identify the stance of more than 128 thousand Twitter users towards Kavanaugh's nomination using both semi-supervised and supervised classification. Next, we quantify the polarization between the different groups in terms of who they retweet and which hashtags they use. We modify existing polarization quantification measures to make them more efficient and more effective. We also characterize the polarization between users who supported and opposed the nomination.

cs.SI↗

arXiv2019

Tanbih: Get To Know What You Are Reading

We introduce Tanbih, a news aggregator with intelligent analysis tools to help readers understanding what's behind a news story. Our system displays news grouped into events and generates media profiles that show the general factuality of reporting, the degree of propagandistic content, hyper-partisanship, leading political ideology, general frame of reporting, and stance with respect to various claims and topics of a news outlet. In addition, we automatically analyse each article to detect whether it is propagandistic and to determine its stance with respect to a number of controversial topics.

cs.CL↗

arXiv2019

Embedding-based Qualitative Analysis of Polarization in Turkey

On June 24, 2018, Turkey conducted a highly-consequential election in which the Turkish people elected their president and parliament in the first election under a new presidential system. During the election period, the Turkish people extensively shared their political opinions on Twitter. One access of polarization among the electorate was support for or opposition to the reelection of Recep Tayyip Erdogan. In this paper, we explore the polarization between the two groups on their political opinions and lifestyle, and examine whether polarization had increased in the lead up to the election. We conduct our analysis on two collected datasets covering the time periods before and during the election period that we split into pro- and anti-Erdogan groups. For the pro and anti splits of both datasets, we generate separate word embedding models, and then use the four generated models to contrast the neighborhood (in the embedding space) of the political leaders, political issues, and lifestyle choices (e.g., beverages, food, and vacation). Our analysis shows that the two groups agree on some topics, such as terrorism and organizations threatening the country, but disagree on others, such as refugees and lifestyle choices. Polarization towards party leaders is more pronounced, and polarization further increased during the election time.

cs.SI↗

arXiv2019

Diacritization of Maghrebi Arabic Sub-Dialects

Diacritization process attempt to restore the short vowels in Arabic written text; which typically are omitted. This process is essential for applications such as Text-to-Speech (TTS). While diacritization of Modern Standard Arabic (MSA) still holds the lion share, research on dialectal Arabic (DA) diacritization is very limited. In this paper, we present our contribution and results on the automatic diacritization of two sub-dialects of Maghrebi Arabic, namely Tunisian and Moroccan, using a character-level deep neural network architecture that stacks two bi-LSTM layers over a CRF output layer. The model achieves word error rate of 2.7% and 3.6% for Moroccan and Tunisian respectively and is capable of implicitly identifying the sub-dialect of the input.

cs.CL↗

arXiv2018

To Kavanaugh or Not to Kavanaugh: That is the Polarizing Question

On October 6, 2018, the US Senate confirmed Brett Kavanaugh with the narrowest margin for a successful confirmation since 1881 and where the senators voted overwhelmingly along party lines. In this paper, we examine whether the political polarization in the Senate is reflected among the general public. To do so, we analyze the views of more than 128 thousand Twitter users. We show that users supporting or opposing Kavanaugh's nomination were generally using divergent hashtags, retweeting different Twitter accounts, and sharing links from different websites. We also examine characterestics of both groups.

cs.SI↗

arXiv2018

Devam vs. Tamam: 2018 Turkish Elections

On June 24, 2018, Turkey held a historical election, transforming its parliamentary system to a presidential one. One of the main questions for Turkish voters was whether to start this new political era with reelecting its long-time political leader Recep Tayyip Erdogan or not. In this paper, we analyzed 108M tweets posted in the two months leading to the election to understand the groups that supported or opposed Erdogan's reelection. We examined the most distinguishing hashtags and retweeted accounts for both groups. Our findings indicate strong polarization between both groups as they differ in terms of ideology, news sources they follow, and preferred TV entertainment.

cs.SI↗

arXiv2017

Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM

Arabic word segmentation is essential for a variety of NLP applications such as machine translation and information retrieval. Segmentation entails breaking words into their constituent stems, affixes and clitics. In this paper, we compare two approaches for segmenting four major Arabic dialects using only several thousand training examples for each dialect. The two approaches involve posing the problem as a ranking problem, where an SVM ranker picks the best segmentation, and as a sequence labeling problem, where a bi-LSTM RNN coupled with CRF determines where best to segment words. We are able to achieve solid segmentation results for all dialects using rather limited training data. We also show that employing Modern Standard Arabic data for domain adaptation and assuming context independence improve overall results.

cs.CL↗

arXiv2017

Seminar Users in the Arabic Twitter Sphere

We introduce the notion of "seminar users", who are social media users engaged in propaganda in support of a political entity. We develop a framework that can identify such users with 84.4% precision and 76.1% recall. While our dataset is from the Arab region, omitting language-specific features has only a minor impact on classification performance, and thus, our approach could work for detecting seminar users in other parts of the world and in other languages. We further explored a controversial political topic to observe the prevalence and potential potency of such users. In our case study, we found that 25% of the users engaged in the topic are in fact seminar users and their tweets make nearly a third of the on-topic tweets. Moreover, they are often successful in affecting mainstream discourse with coordinated hashtag campaigns.

cs.SI↗