arXiv subjects

Svetlana Kiritchenko

Publications and source records attributed to Svetlana Kiritchenko.

35 records · Page 2Linked to original sources

arXiv2022

Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors

Robustness of machine learning models on ever-changing real-world data is critical, especially for applications affecting human well-being such as content moderation. New kinds of abusive language continually emerge in online discussions in response to current events (e.g., COVID-19), and the deployed abuse detection systems should be updated regularly to remain accurate. In this paper, we show that general abusive language classifiers tend to be fairly reliable in detecting out-of-domain explicitly abusive utterances but fail to detect new types of more subtle, implicit abuse. Next, we propose an interpretability technique, based on the Testing Concept Activation Vector (TCAV) method from computer vision, to quantify the sensitivity of a trained model to the human-defined concepts of explicit and implicit abusive language, and use that to explain the generalizability of the model on new data, in this case, COVID-related anti-Asian hate speech. Extending this technique, we introduce a novel metric, Degree of Explicitness, for a single instance and show that the new metric is beneficial in suggesting out-of-domain unlabeled examples to effectively enrich the training data with informative, implicitly abusive texts.

cs.CL↗

arXiv2021

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm. Significant effort in Natural Language Processing (NLP) research has been devoted to addressing this problem through abusive content detection and related sub-areas, such as the detection of hate speech, toxicity, cyberbullying, etc. Although current technologies achieve high classification performance in research studies, it has been observed that the real-life application of this technology can cause unintended harms, such as the silencing of under-represented groups. We review a large body of NLP research on automatic abuse detection with a new focus on ethical challenges, organized around eight established ethical principles: privacy, accountability, safety and security, transparency and explainability, fairness and non-discrimination, human control of technology, professional responsibility, and promotion of human values. In many cases, these principles relate not only to situational ethical codes, which may be context-dependent, but are in fact connected to universal human rights, such as the right to privacy, freedom from discrimination, and freedom of expression. We highlight the need to examine the broad social impacts of this technology, and to bring ethical and human rights considerations to every stage of the application life-cycle, from task formulation and dataset design, to model training and evaluation, to application deployment. Guided by these principles, we identify several opportunities for rights-respecting, socio-technical solutions to detect and confront online abuse, including `nudging', `quarantining', value sensitive design, counter-narratives, style transfer, and AI-driven public education applications.

cs.CL↗

arXiv2021

Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model

Stereotypical language expresses widely-held beliefs about different social categories. Many stereotypes are overtly negative, while others may appear positive on the surface, but still lead to negative consequences. In this work, we present a computational approach to interpreting stereotypes in text through the Stereotype Content Model (SCM), a comprehensive causal theory from social psychology. The SCM proposes that stereotypes can be understood along two primary dimensions: warmth and competence. We present a method for defining warmth and competence axes in semantic embedding space, and show that the four quadrants defined by this subspace accurately represent the warmth and competence concepts, according to annotated lexicons. We then apply our computational SCM model to textual stereotype data and show that it compares favourably with survey-based studies in the psychological literature. Furthermore, we explore various strategies to counter stereotypical beliefs with anti-stereotypes. It is known that countering stereotypes with anti-stereotypical examples is one of the most effective ways to reduce biased thinking, yet the problem of generating anti-stereotypes has not been previously studied. Thus, a better understanding of how to generate realistic and effective anti-stereotypes can contribute to addressing pressing societal concerns of stereotyping, prejudice, and discrimination.

cs.CY↗

arXiv2021

On Cross-Dataset Generalization in Automatic Detection of Online Abuse

NLP research has attained high performances in abusive language detection as a supervised classification task. While in research settings, training and test datasets are usually obtained from similar data samples, in practice systems are often applied on data that are different from the training set in topic and class distributions. Also, the ambiguity in class definitions inherited in this task aggravates the discrepancies between source and target datasets. We explore the topic bias and the task formulation bias in cross-dataset generalization. We show that the benign examples in the Wikipedia Detox dataset are biased towards platform-specific topics. We identify these examples using unsupervised topic modeling and manual inspection of topics' keywords. Removing these topics increases cross-dataset generalization, without reducing in-domain classification performance. For a robust dataset design, we suggest applying inexpensive unsupervised methods to inspect the collected data and downsize the non-generalizable content before manually annotating for class labels.

cs.CL↗

arXiv2020

Towards Ethics by Design in Online Abusive Content Detection

To support safety and inclusion in online communications, significant efforts in NLP research have been put towards addressing the problem of abusive content detection, commonly defined as a supervised classification task. The research effort has spread out across several closely related sub-areas, such as detection of hate speech, toxicity, cyberbullying, etc. There is a pressing need to consolidate the field under a common framework for task formulation, dataset design and performance evaluation. Further, despite current technologies achieving high classification accuracies, several ethical issues have been revealed. We bring ethical issues to forefront and propose a unified framework as a two-step process. First, online content is categorized around personal and identity-related subject matters. Second, severity of abuse is identified through comparative annotation within each category. The novel framework is guided by the Ethics by Design principle and is a step towards building more accurate and trusted models.

cs.CL↗

arXiv2020

SOLO: A Corpus of Tweets for Examining the State of Being Alone

The state of being alone can have a substantial impact on our lives, though experiences with time alone diverge significantly among individuals. Psychologists distinguish between the concept of solitude, a positive state of voluntary aloneness, and the concept of loneliness, a negative state of dissatisfaction with the quality of one's social interactions. Here, for the first time, we conduct a large-scale computational analysis to explore how the terms associated with the state of being alone are used in online language. We present SOLO (State of Being Alone), a corpus of over 4 million tweets collected with query terms 'solitude', 'lonely', and 'loneliness'. We use SOLO to analyze the language and emotions associated with the state of being alone. We show that the term 'solitude' tends to co-occur with more positive, high-dominance words (e.g., enjoy, bliss) while the terms 'lonely' and 'loneliness' frequently co-occur with negative, low-dominance words (e.g., scared, depressed), which confirms the conceptual distinctions made in psychology. We also show that women are more likely to report on negative feelings of being lonely as compared to men, and there are more teenagers among the tweeters that use the word 'lonely' than among the tweeters that use the word 'solitude'.

cs.CL↗

arXiv2019

SemEval-2015 Task 10: Sentiment Analysis in Twitter

In this paper, we describe the 2015 iteration of the SemEval shared task on Sentiment Analysis in Twitter. This was the most popular sentiment analysis shared task to date with more than 40 teams participating in each of the last three years. This year's shared task competition consisted of five sentiment prediction subtasks. Two were reruns from previous years: (A) sentiment expressed by a phrase in the context of a tweet, and (B) overall sentiment of a tweet. We further included three new subtasks asking to predict (C) the sentiment towards a topic in a single tweet, (D) the overall sentiment towards a topic in a set of tweets, and (E) the degree of prior polarity of a phrase.

cs.CL↗

arXiv2018

Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems

Automatic machine learning systems can inadvertently accentuate and perpetuate inappropriate human biases. Past work on examining inappropriate biases has largely focused on just individual systems. Further, there is no benchmark dataset for examining inappropriate biases in systems. Here for the first time, we present the Equity Evaluation Corpus (EEC), which consists of 8,640 English sentences carefully chosen to tease out biases towards certain races and genders. We use the dataset to examine 219 automatic sentiment analysis systems that took part in a recent shared task, SemEval-2018 Task 1 'Affect in Tweets'. We find that several of the systems show statistically significant bias; that is, they consistently provide slightly higher sentiment intensity predictions for one race or one gender. We make the EEC freely available.

cs.CL↗

arXiv2018

Sentiment Composition of Words with Opposing Polarities

In this paper, we explore sentiment composition in phrases that have at least one positive and at least one negative word---phrases like 'happy accident' and 'best winter break'. We compiled a dataset of such opposing polarity phrases and manually annotated them with real-valued scores of sentiment association. Using this dataset, we analyze the linguistic patterns present in opposing polarity phrases. Finally, we apply several unsupervised and supervised techniques of sentiment composition to determine their efficacy on this dataset. Our best system, which incorporates information from the phrase's constituents, their parts of speech, their sentiment association scores, and their embedding vectors, obtains an accuracy of over 80% on the opposing polarity phrases.

cs.CL↗

arXiv2018

NRC-Canada at SMM4H Shared Task: Classifying Tweets Mentioning Adverse Drug Reactions and Medication Intake

Our team, NRC-Canada, participated in two shared tasks at the AMIA-2017 Workshop on Social Media Mining for Health Applications (SMM4H): Task 1 - classification of tweets mentioning adverse drug reactions, and Task 2 - classification of tweets describing personal medication intake. For both tasks, we trained Support Vector Machine classifiers using a variety of surface-form, sentiment, and domain-specific features. With nine teams participating in each task, our submissions ranked first on Task 1 and third on Task 2. Handling considerable class imbalance proved crucial for Task 1. We applied an under-sampling technique to reduce class imbalance (from about 1:10 to 1:2). Standard n-gram features, n-grams generalized over domain terms, as well as general-domain and domain-specific word embeddings had a substantial impact on the overall performance in both tasks. On the other hand, including sentiment lexicon features did not result in any improvement.

cs.CL↗

arXiv2017

Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best-Worst Scaling

Access to word-sentiment associations is useful for many applications, including sentiment analysis, stance detection, and linguistic analysis. However, manually assigning fine-grained sentiment association scores to words has many challenges with respect to keeping annotations consistent. We apply the annotation technique of Best-Worst Scaling to obtain real-valued sentiment association scores for words and phrases in three different domains: general English, English Twitter, and Arabic Twitter. We show that on all three domains the ranking of words by sentiment remains remarkably consistent even when the annotation process is repeated with a different set of annotators. We also, for the first time, determine the minimum difference in sentiment association that is perceptible to native speakers of a language.

cs.CL↗

arXiv2017

Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation

Rating scales are a widely used method for data annotation; however, they present several challenges, such as difficulty in maintaining inter- and intra-annotator consistency. Best-worst scaling (BWS) is an alternative method of annotation that is claimed to produce high-quality annotations while keeping the required number of annotations similar to that of rating scales. However, the veracity of this claim has never been systematically established. Here for the first time, we set up an experiment that directly compares the rating scale method with BWS. We show that with the same total number of annotations, BWS produces significantly more reliable results than the rating scale.

cs.CL↗

arXiv2017

The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition

Negators, modals, and degree adverbs can significantly affect the sentiment of the words they modify. Often, their impact is modeled with simple heuristics; although, recent work has shown that such heuristics do not capture the true sentiment of multi-word phrases. We created a dataset of phrases that include various negators, modals, and degree adverbs, as well as their combinations. Both the phrases and their constituent content words were annotated with real-valued scores of sentiment association. Using phrasal terms in the created dataset, we analyze the impact of individual modifiers and the average effect of the groups of modifiers on overall sentiment. We find that the effect of modifiers varies substantially among the members of the same group. Furthermore, each individual modifier can affect sentiment words in different ways. Therefore, solutions based on statistical learning seem more promising than fixed hand-crafted rules on the task of automatic sentiment prediction.

cs.CL↗

arXiv2016

Stance and Sentiment in Tweets

We can often detect from a person's utterances whether he/she is in favor of or against a given target entity -- their stance towards the target. However, a person may express the same stance towards a target by using negative or positive language. Here for the first time we present a dataset of tweet--target pairs annotated for both stance and sentiment. The targets may or may not be referred to in the tweets, and they may or may not be the target of opinion in the tweets. Partitions of this dataset were used as training and test sets in a SemEval-2016 shared task competition. We propose a simple stance detection system that outperforms submissions from all 19 teams that participated in the shared task. Additionally, access to both stance and sentiment annotations allows us to explore several research questions. We show that while knowing the sentiment expressed by a tweet is beneficial for stance classification, it alone is not sufficient. Finally, we use additional unlabeled data through distant supervision techniques and word embeddings to further improve stance classification.

cs.CL↗

arXiv2013

Identifying Purpose Behind Electoral Tweets

Tweets pertaining to a single event, such as a national election, can number in the hundreds of millions. Automatically analyzing them is beneficial in many downstream natural language applications such as question answering and summarization. In this paper, we propose a new task: identifying the purpose behind electoral tweets--why do people post election-oriented tweets? We show that identifying purpose is correlated with the related phenomenon of sentiment and emotion detection, but yet significantly different. Detecting purpose has a number of applications including detecting the mood of the electorate, estimating the popularity of policies, identifying key issues of contention, and predicting the course of events. We create a large dataset of electoral tweets and annotate a few thousand tweets for purpose. We develop a system that automatically classifies electoral tweets as per their purpose, obtaining an accuracy of 43.56% on an 11-class task and an accuracy of 73.91% on a 3-class task (both accuracies well above the most-frequent-class baseline). Finally, we show that resources developed for emotion detection are also helpful for detecting purpose.

cs.CL↗

arXiv2013

Using Nuances of Emotion to Identify Personality

Past work on personality detection has shown that frequency of lexical categories such as first person pronouns, past tense verbs, and sentiment words have significant correlations with personality traits. In this paper, for the first time, we show that fine affect (emotion) categories such as that of excitement, guilt, yearning, and admiration are significant indicators of personality. Additionally, we perform experiments to show that the gains provided by the fine affect categories are not obtained by using coarse affect categories alone or with specificity features alone. We employ these features in five SVM classifiers for detecting five personality traits through essays. We find that the use of fine emotion features leads to statistically significant improvement over a competitive baseline, whereas the use of coarse affect and specificity features does not.

cs.CL↗

arXiv2013

NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets

In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a submissions stood first in both tasks on tweets, obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. We implemented a variety of surface-form, semantic, and sentiment features. with sentiment-word hashtags, and one from tweets with emoticons. In the message-level task, the lexicon-based features provided a gain of 5 F-score points over all others. Both of our systems can be replicated us available resources.

cs.CL↗