• Publications
  • Influence
Explaining machine learning classifiers through diverse counterfactual explanations
This work proposes a framework for generating and evaluating a diverse set of counterfactual explanations based on determinantal point processes, and provides metrics that enable comparison ofcounterfactual-based methods to other local explanation methods. Expand
Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
It is shown that persuasive arguments are characterized by interesting patterns of interaction dynamics, such as participant entry-order and degree of back-and-forth exchange, and that stylistic choices in how the opinion is expressed carry predictive power. Expand
User-level sentiment analysis incorporating social networks
It is shown that information about social relationships can be used to improve user-level sentiment analysis and incorporating social-network information can indeed lead to statistically significant sentiment classification improvements over the performance of an approach based on Support Vector Machines having access only to textual features. Expand
The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter
Consider a person trying to spread an important message on a social network. He/she can spend hours trying to craft the message. Does it actually matter? While there has been extensive prior workExpand
Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
The problem of feasibility is formulated as preserving causal relationships among input features and a method is presented that uses (partial) structural causal models to generate actionable counterfactuals that better satisfy feasibility constraints than existing methods. Expand
Creative Writing with a Machine in the Loop: Case Studies on Slogans and Stories
Novel natural language models and design choices are suggested that may better support creative writing, as machine suggestions do not necessarily lead to better written artifacts. Expand
On the Interplay between Social and Topical Structure
The interface of two decisive structures forming the backbone of online social media is examined: the graph structure of social networks - who connects with whom - and the set structure of topical affiliations - who is interested in what, and computationally simple structural determinants can provide remarkable performance in both tasks. Expand
On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
This paper uses deception detection as a testbed and investigates how to harness explanations and predictions of machine learning models to improve human performance while retaining human agency, and demonstrates a tradeoff between human performance and human agency. Expand
Neural Models for Documents with Metadata
A general neural framework is proposed, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration of alternative models, and achieves strong performance, with a manageable tradeoff between perplexity, coherence, and sparsity. Expand
Dynamic Entity Representations in Neural Language Models
A new type of language model is presented that can explicitly model entities, dynamically update their representations, and contextually generate their mentions and can model an arbitrary number of entities in context while generating each entity mention at an arbitrary length. Expand