Hate speech in the form of racist and sexist remarks are a common occurrence on social media. For that reason, many social media services address the problem of identifying hate speech, but the definition of hate speech varies markedly and is largely a manual effort (BBC, 2015; Lomas, 2015). We provide a list of criteria founded in critical race theory, and use them to annotate a publicly available corpus of more than 16k tweets. We analyze the impact of various extra-linguistic features in conjunction with character n-grams for hatespeech detection. We also present a dictionary based the most indicative words in our data.

/pdf/hateful-symbols-or-hateful-people-predictive-features-for-4ob7ivium7.pdf

Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter

The past decade has seen an explosion in the amount of digital information stored in electronic health records (EHRs). While primarily designed for archiving patient information and performing administrative healthcare tasks like billing, many researchers have found secondary use of these records for various clinical informatics applications. Over the same period, the machine learning community has seen widespread advances in the field of deep learning. In this review, we survey the current research on applying deep learning to clinical tasks based on EHR data, where we find a variety of deep learning techniques and frameworks being applied to several types of clinical applications including information extraction, representation learning, outcome prediction, phenotyping, and deidentification. We identify several limitations of current research involving topics such as model interpretability, data heterogeneity, and lack of universal benchmarks. We conclude by summarizing the state of the field and identifying avenues of future deep EHR research.

/pdf/deep-ehr-a-survey-of-recent-advances-in-deep-learning-4bsjsfwuuq.pdf

Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis

A Virtuous Circle: Political Communications in Postindustrial Societies. Pippa Norris. New York: Cambridge University Press, 2000. 398 pp. $59.95 hbk. $21.95 pbk. The main finding of Pippa Norris's study is that exposure to the news media is positively related to citizens' levels of political knowledge, trust, and participation, even after controlling for demographics, attitudinal factors, and cultural differences. Although various positive contributions of exposure to news media already have been documented in other research, never was the amount of evidence as monumental as in this book. Norris analyzed European Community, Eurobarometer, European Election and Post-election, British Campaign Panel, U.S. National Election, and Pew Center for the People and the Press surveys, providing individual and aggregate level, over-time and cross-sectional evidence supporting her virtuous media thesis. The book is set up as a challenge to "conventional wisdom" or "unquestioned orthodoxy" of media malaise theories that argue that "exposure to the news media discourages learning about politics, erodes trust in political leaders and government institutions, and dampens political mobilization." The problem is that there is a huge gap between the abundance of glib charges and the scarcity of empirical evidence of negative effects of news media. Consequently, Norris mostly relies on Michael Robinson's long ago retracted videomalaise claim and strays away from her main line of theorizing by reviewing studies that deal with the issues well outside the scope of her own study, such as effects of framing news stories, political advertising, and television entertainment. Findings of negative media effects in contexts other than elections and those tapping more specific types of media content and their particular features remain unchallenged by the Norris study. Norris acknowledges that "we need to compare the effects of variance in the media messages so that we can see whether people who consistently use one distinctive source (such as crime-focused local TV news) differ from those who use others (such as rightwing talk radio)" and that "our measures of media habits are often diffuse and imprecise," but she is still restricted in her research to measures of frequency of general newspaper and television news use. Nevertheless, Norris urges us to stopblaming the news media for political problems and instead to direct our attention to "the problems themselves." This call, without showing that media in many of their specific content characteristics or structures are not a part of problems that extend beyond voting and political campaigning, seems premature at best. However, Norris's study makes a significant contribution to communication research by most convincingly showing that the news media may be an important part of solutions to some of the social ills. …

A Virtuous Circle: Political Communications in Postindustrial Societies

语用学新解 : [英文版] = Understanding Pragmatics

As the body of research on abusive language detection and analysis grows, there is a need for critical consideration of the relationships between different subtasks that have been grouped under this label. Based on work on hate speech, cyberbullying, and online abuse we propose a typology that captures central similarities and differences between subtasks and discuss the implications of this for data annotation and feature construction. We emphasize the practical actions that can be taken by researchers to best approach their abusive language detection subtask of interest.

/pdf/understanding-abuse-a-typology-of-abusive-language-detection-qi63tebmbk.pdf

Understanding Abuse: A Typology of Abusive Language Detection Subtasks.

We present a dictionary-based approach to racism detection in Dutch social media comments, which were retrieved from two public Belgian social media sites likely to attract racist reactions. These comments were labeled as racist or non-racist by multiple annotators. For our approach, three discourse dictionaries were created: first, we created a dictionary by retrieving possibly racist and more neutral terms from the training data, and then augmenting these with more general words to remove some bias. A second dictionary was created through automatic expansion using a \texttt{word2vec} model trained on a large corpus of general Dutch text. Finally, a third dictionary was created by manually filtering out incorrect expansions. We trained multiple Support Vector Machines, using the distribution of words over the different categories in the dictionaries as features. The best-performing model used the manually cleaned dictionary and obtained an F-score of 0.46 for the racist class on a test set consisting of unseen Dutch comments, retrieved from the same sites used for the training set. The automated expansion of the dictionary only slightly boosted the model's performance, and this increase in performance was not statistically significant. The fact that the coverage of the expanded dictionaries did increase indicates that the words that were automatically added did occur in the corpus, but were not able to meaningfully impact performance. The dictionaries, code, and the procedure for requesting the corpus are available at: this https URL

https://www.amicaproject.be/sites/amicaproject.be/files/dictionary-based-approach.pdf

A Dictionary-based Approach to Racism Detection in Dutch Social Media

We present two experiments on the automated detection of racist discourse in Dutch social media. In both experiments, multiple classifiers are trained on the same training set. This training set consists of Dutch posts retrieved from two public Belgian social media pages which are likely to attract racist reactions. The posts were labeled as racist or non-racist by multiple annotators, who reached an acceptable agreement score. The different classification models all use the Support Vector Machine algorithm, but use different (sets of) linguistic features, which can be lexical, stylistic or dictionary-based. In the first experiment, the models are evaluated on a test set containing unseen comments retrieved from the same pages as the training set (and thus also skewed towards racism). In the second experiment, the same models from Experiment 1 are tested on an alternative test set, containing more neutral comments, retrieved from the social media page of a Belgian newspaper. In both experiments, the best performing model relies on a dictionary containing different word categories specifically related to racist discourse. It reaches an F-score of 0.47 (exp. 1) and 0.40 (exp. 2) for the racist class and ROC Area Under Curve scores of 0.64 (exp. 1) and 0.73 (exp. 2). The dictionaries, code, and the procedure for requesting the corpus are available at: https://github.com/clips/hades

/pdf/the-automated-detection-of-racist-discourse-in-dutch-social-3t0wknu682.pdf

The Automated Detection of Racist Discourse in Dutch Social Media

In this paper, we report a knowledge-based method for Word Sense Disambiguation in the domains of biomedical and clinical text. We combine word representations created on large corpora with a small number of definitions from the UMLS to create concept representations, which we then compare to representations of the context of ambiguous terms. Using no relational information, we obtain comparable performance to previous approaches on the MSH-WSD dataset, which is a well-known dataset in the biomedical domain. Additionally, our method is fast and easy to set up and extend to other domains. Supplementary materials, including source code, can be found at https: //github.com/clips/yarn

/pdf/using-distributed-representations-to-disambiguate-biomedical-2pc203lsjl.pdf

Using Distributed Representations to Disambiguate Biomedical and Clinical Concepts

We present a simple but effective method for aspect identification in sentiment analysis. Our unsupervised method only requires word embeddings and a POS tagger, and is therefore straightforward to apply to new domains and languages. We introduce Contrastive Attention (CAt), a novel single-head attention mechanism based on an RBF kernel, which gives a considerable boost in performance and makes the model interpretable. Previous work relied on syntactic features and complex neural models. We show that given the simplicity of current benchmark datasets for aspect extraction, such complex models are not needed. The code to reproduce the experiments reported in this paper is available at this https URL

Embarrassingly Simple Unsupervised Aspect Extraction

Clinical NLP has an immense potential in contributing to how clinical practice will be revolutionized by the advent of large scale processing of clinical records. However, this potential has remained largely untapped due to slow progress primarily caused by strict data access policies for researchers. In this paper, we discuss the concern for privacy and the measures it entails. We also suggest sources of less sensitive data. Finally, we draw attention to biases that can compromise the validity of empirical research and lead to socially harmful applications.

/pdf/a-short-review-of-ethical-challenges-in-clinical-natural-3zl0mk0byv.pdf

Stéphan Tulkens

Papers

A Dictionary-based Approach to Racism Detection in Dutch Social Media

The Automated Detection of Racist Discourse in Dutch Social Media

Using Distributed Representations to Disambiguate Biomedical and Clinical Concepts

Embarrassingly Simple Unsupervised Aspect Extraction

A Short Review of Ethical Challenges in Clinical Natural Language Processing