arXiv subjects

Nithum Thain

Publications and source records attributed to Nithum Thain.

27 records · Page 2Linked to original sources

arXiv2020

Classifying Constructive Comments

We introduce the Constructive Comments Corpus (C3), comprised of 12,000 annotated news comments, intended to help build new tools for online communities to improve the quality of their discussions. We define constructive comments as high-quality comments that make a contribution to the conversation. We explain the crowd worker annotation scheme and define a taxonomy of sub-characteristics of constructiveness. The quality of the annotation scheme and the resulting dataset is evaluated using measurements of inter-annotator agreement, expert assessment of a sample, and by the constructiveness sub-characteristics, which we show provide a proxy for the general constructiveness concept. We provide models for constructiveness trained on C3 using both feature-based and a variety of deep learning approaches and demonstrate that these models capture general rather than topic- or domain-specific characteristics of constructiveness, through domain adaptation experiments. We examine the role that length plays in our models, as comment length could be easily gamed if models depend heavily upon this feature. By examining the errors made by each model and their distribution by length, we show that the best performing models are less correlated with comment length.The constructiveness corpus and our experiments pave the way for a moderation tool focused on promoting comments that make a contribution, rather than only filtering out undesirable content.

cs.CL↗

arXiv2020

Toxicity Detection: Does Context Really Matter?

Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that comments maybe judged independently. We investigate this assumption by focusing on two questions: (a) does context affect the human judgement, and (b) does conditioning on context improve performance of toxicity detection systems? We experiment with Wikipedia conversations, limiting the notion of context to the previous post in the thread and the discussion title. We find that context can both amplify or mitigate the perceived toxicity of posts. Moreover, a small but significant subset of manually labeled posts (5% in one of our experiments) end up having the opposite toxicity labels if the annotators are not provided with context. Surprisingly, we also find no evidence that context actually improves the performance of toxicity classifiers, having tried a range of classifiers and mechanisms to make them context aware. This points to the need for larger datasets of comments annotated in context. We make our code and data publicly available.

cs.CL↗

arXiv2019

Debiasing Embeddings for Reduced Gender Bias in Text Classification

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation classification (De-Arteaga et al.,2019). We show that traditional techniques for debiasing embeddings can actually worsen the bias of the downstream classifier by providing a less noisy channel for communicating gender information. With a relatively minor adjustment, however, we show how these same techniques can be used to simultaneously reduce bias and maintain high classification accuracy.

cs.LG↗

arXiv2019

Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification

Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier's score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models.

cs.LG↗

arXiv2019

Limitations of Pinned AUC for Measuring Unintended Bias

This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric. However, as we highlight in this report, there are ways that the metric can obscure different kinds of unintended biases when the underlying class distributions on which bias is being measured are not carefully controlled.

stat.ML↗

arXiv2018

WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community

We present a corpus that encompasses the complete history of conversations between contributors to Wikipedia, one of the largest online collaborative communities. By recording the intermediate states of conversations---including not only comments and replies, but also their modifications, deletions and restorations---this data offers an unprecedented view of online conversation. This level of detail supports new research questions pertaining to the process (and challenges) of large-scale online collaboration. We illustrate the corpus' potential with two case studies that highlight new perspectives on earlier work. First, we explore how a person's conversational behavior depends on how they relate to the discussion's venue. Second, we show that community moderation of toxic behavior happens at a higher rate than previously estimated. Finally the reconstruction framework is designed to be language agnostic, and we show that it can extract high quality conversational data in both Chinese and English.

cs.CL↗

arXiv2018

Conversations Gone Awry: Detecting Early Signs of Conversational Failure

One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very start of a conversation whether it will get out of hand. As opposed to detecting undesirable behavior after the fact, this task aims to enable early, actionable prediction at a time when the conversation might still be salvaged. To this end, we develop a framework for capturing pragmatic devices---such as politeness strategies and rhetorical prompts---used to start a conversation, and analyze their relation to its future trajectory. Applying this framework in a controlled setting, we demonstrate the feasibility of detecting early warning signs of antisocial behavior in online discussions.

cs.CL↗

arXiv2017

Ex Machina: Personal Attacks Seen at Scale

The damage personal attacks cause to online discourse motivates many platforms to try to curb the phenomenon. However, understanding the prevalence and impact of personal attacks in online platforms at scale remains surprisingly difficult. The contribution of this paper is to develop and illustrate a method that combines crowdsourcing and machine learning to analyze personal attacks at scale. We show an evaluation method for a classifier in terms of the aggregated number of crowd-workers it can approximate. We apply our methodology to English Wikipedia, generating a corpus of over 100k high quality human-labeled comments and 63M machine-labeled ones from a classifier that is as good as the aggregate of 3 crowd-workers, as measured by the area under the ROC curve and Spearman correlation. Using this corpus of machine-labeled scores, our methodology allows us to explore some of the open questions about the nature of online personal attacks. This reveals that the majority of personal attacks on Wikipedia are not the result of a few malicious users, nor primarily the consequence of allowing anonymous contributions from unregistered users.

cs.CL↗

arXiv2012

On the Implications of Lookahead Search in Game Playing

Lookahead search is perhaps the most natural and widely used game playing strategy. Given the practical importance of the method, the aim of this paper is to provide a theoretical performance examination of lookahead search in a wide variety of applications. To determine a strategy play using lookahead search}, each agent predicts multiple levels of possible re-actions to her move (via the use of a search tree), and then chooses the play that optimizes her future payoff accounting for these re-actions. There are several choices of optimization function the agents can choose, where the most appropriate choice of function will depend on the specifics of the actual game - we illustrate this in our examples. Furthermore, the type of search tree chosen by computationally-constrained agent can vary. We focus on the case where agents can evaluate only a bounded number, $k$, of moves into the future. That is, we use depth $k$ search trees and call this approach {\em k-lookahead search}. We apply our method in five well-known settings: AdWord auctions; industrial organization (Cournot's model); congestion games; valid-utility games and basic-utility games; cost-sharing network design games. We consider two questions. First, what is the expected social quality of outcome when agents apply lookahead search? Second, what interactive behaviours can be exhibited when players use lookahead search?

cs.GT↗