Predicting the political bias and the factuality of reporting of entire news outlets are critical elements of media profiling, which is an understudied but an increasingly important research direction.The present level of proliferation of fake, biased, and propagandistic content online, has made it impossible to fact-check every single suspicious claim, either manually or automatically.Alternatively, we can profile entire news outlets and look for those that are likely to publish fake or biased content.This approach makes it possible to detect likely "fake news" the moment they are published, by simply checking the reliability of their source.From a practical perspective, political bias and factuality of reporting have a linguistic aspect but also a social context.Here, we study the impact of both, namely (i) what was written (i.e., what was published by the target medium, and how it describes itself on Twitter) vs. (ii) who read it (i.e., analyzing the readers of the target medium on Facebook, Twitter, and YouTube).We further study (iii) what was written about the target medium on Wikipedia.The evaluation results show that what was written matters most, and that putting all information sources together yields huge improvements over the current state-of-the-art.

We explore the task of predicting the leading political ideology or bias of news articles.First, we collect and release a large dataset of 34,737 articles that were manually annotated for political ideology -left, center, or right-, which is well-balanced across both topics and media.We further use a challenging experimental setup where the test examples come from media that were not seen during training, which prevents the model from learning to detect the source of the target news article instead of predicting its political ideology.From a modeling perspective, we propose an adversarial media adaptation, as well as a specially adapted triplet loss.We further add background information about the source, and we show that it is quite helpful for improving article-level prediction.Our experimental results show very sizable improvements over using state-of-the-art pre-trained Transformers in this challenging setup.

Opinion-mining or sentiment analysis continues to gain interest in industry and academics. While there has been significant progress in developing models for sentiment analysis, the field remains an active area of research for many languages across the world, and in particular for the Arabic language, which is the fifth most-spoken language and has become the fourth most-used language on the Internet. With the flurry of research activity in Arabic opinion mining, several researchers have provided surveys to capture advances in the field. While these surveys capture a wealth of important progress in the field, the fast pace of advances in machine learning and natural language processing (NLP) necessitates a continuous need for a more up-to-date literature survey. The aim of this article is to provide a comprehensive literature survey for state-of-the-art advances in Arabic opinion mining. The survey goes beyond surveying previous works that were primarily focused on classification models. Instead, this article provides a comprehensive system perspective by covering advances in different aspects of an opinion-mining system, including advances in NLP software tools, lexical sentiment and corpora resources, classification models, and applications of opinion mining. It also presents future directions for opinion mining in Arabic. The survey also covers latest advances in the field, including deep learning advances in Arabic Opinion Mining. The article provides state-of-the-art information to help new or established researchers in the field as well as industry developers who aim to deploy an operational complete opinion-mining system. Key insights are captured at the end of each section for particular aspects of the opinion-mining system giving the reader a choice of focusing on particular aspects of interest.

We present a study on predicting the factuality of reporting and bias of news media.While previous work has focused on studying the veracity of claims or documents, here we are interested in characterizing entire news media.These are under-studied but arguably important research problems, both in their own right and as a prior for fact-checking systems.We experiment with a large list of news websites and with a rich set of features derived from (i) a sample of articles from the target news medium, (ii) its Wikipedia page, (iii) its Twitter account, (iv) the structure of its URL, and (v) information about the Web traffic it attracts.The experimental results show sizable performance gains over the baselines, and confirm the importance of each feature type.

Mitra Mohtarami, Ramy Baly, James Glass, Preslav Nakov, Lluís Màrquez, Alessandro Moschitti. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Accurate sentiment analysis models encode the sentiment of words and their combinations to predict the overall sentiment of a sentence. This task becomes challenging when applied to morphologically rich languages (MRL). In this article, we evaluate the use of deep learning advances, namely the Recursive Neural Tensor Networks (RNTN), for sentiment analysis in Arabic as a case study of MRLs. While Arabic may not be considered the only representative of all MRLs, the challenges faced and proposed solutions in Arabic are common to many other MRLs. We identify, illustrate, and address MRL-related challenges and show how RNTN is affected by the morphological richness and orthographic ambiguity of the Arabic language. To address the challenges with sentiment extraction from text in MRL, we propose to explore different orthographic features as well as different morphological features at multiple levels of abstraction ranging from raw words to roots. A key requirement for RNTN is the availability of a sentiment treebank; a collection of syntactic parse trees annotated for sentiment at all levels of constituency and that currently only exists in English. Therefore, our contribution also includes the creation of the first Arabic Sentiment Treebank (A r S en TB) that is morphologically and orthographically enriched. Experimental results show that, compared to the basic RNTN proposed for English, our solution achieves significant improvements up to 8% absolute at the phrase level and 10.8% absolute at the sentence level, measured by average F1 score. It also outperforms well-known classifiers including Support Vector Machines, Recursive Auto Encoders, and Long Short-Term Memory by 7.6%, 3.2%, and 1.6% absolute respectively, all models being trained with similar morphological considerations.

While research on English opinion mining has already achieved significant progress and success, work on Arabic opinion mining is still lagging. This is mainly due to the relative recency of research efforts in developing natural language processing (NLP) methods for Arabic, handling its morphological complexity, and the lack of large-scale opinion resources for Arabic. To close this gap, we examine the class of models used for English and that do not require extensive use of NLP or opinion resources. In particular, we consider the Recursive Auto Encoder (RAE). However, RAE models are not as successful in Arabic as they are in English, due to their limitations in handling the morphological complexity of Arabic, providing a more complete and comprehensive input features for the auto encoder, and performing semantic composition following the natural way constituents are combined to express the overall meaning. In this article, we propose A R ecursive Deep Learning Model for O pinion M ining in A rabic (AROMA) that addresses these limitations. AROMA was evaluated on three Arabic corpora representing different genres and writing styles. Results show that AROMA achieved significant performance improvements compared to the baseline RAE. It also outperformed several well-known approaches in the literature.

Evaluation of machine translation (MT) into morphologically rich languages (MRL) has not been well studied despite posing many challenges. In this paper, we explore the use of embeddings obtained from different levels of lexical and morpho-syntactic linguistic analysis and show that they improve MT evaluation into an MRL. Specifically we report on Arabic, a language with complex and rich morphology. Our results show that using a neural-network model with different input representations produces results that clearly outperform the state-of-the-art for MT evaluation into Arabic, by almost over 75% increase in correlation with human judgments on pairwise MT evaluation quality task. More importantly, we demonstrate the usefulness of morpho-syntactic representations to model sentence similarity for MT evaluation and address complex linguistic phenomena of Arabic.

This article introduces a sentiment analysis approach that adopts the way humans read, interpret, and extract sentiment from text. Our motivation builds on the assumption that human interpretation should lead to the most accurate assessment of sentiment in text. We call this automated process Human Reading for Sentiment (HRS). Previous research in sentiment analysis has produced many frameworks that can fit one or more of the HRS aspects; however, none of these methods has addressed them all in one approach. HRS provides a meta-framework for developing new sentiment analysis methods or improving existing ones. The proposed framework provides a theoretical lens for zooming in and evaluating aspects of any sentiment analysis method to identify gaps for improvements towards matching the human reading process. Key steps in HRS include the automation of humans low-level and high-level cognitive text processing. This methodology paves the way towards the integration of psychology with computational linguistics and machine learning to employ models of pragmatics and discourse analysis for sentiment analysis. HRS is tested with two state-of-the-art methods; one is based on feature engineering, and the other is based on deep learning. HRS highlighted the gaps in both methods and showed improvements for both.