Why-oriented end-user debugging of naive Bayes text classification

By Todd Kulesza, Simone Stumpf, Weng-Keen Wong, Margaret M. Burnett, Stephen Perona, Amy J. Ko, Ian Oberst. 2011

99 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications, Software

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

In Software

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “(Doshi-Velez and Kim, 2017; J. Doyle, Radzicki, and Trees, 2008; Freitas, 2014; Groce et al., 2014; Kulesza et al., 2011; Kulesza, Stumpf, Burnett, and Kwan, 2012; T. Miller, 2017; T. Miller et al., 2017; Pacer, Williams, Chen, Lombrozo, and Griffiths, 2013; Sauro and Dumas, 2009; Shinsel et al.,…”
Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, background): “Already, projects of this type are underway, with impressive results; for example, see [91, 89, 156].”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “of why-oriented explanation systems in debugging a naı̈ve Bayes learning model for text classification and in context-aware applications were respectively tested in [345, 60] and [346, 78].”
The Role of Explanations in Assessing and Correcting Personalized Intelligent Agents (2012, methodology): “Thus, we conducted a follow-up study to categorize the barriers and information needs that end users encounter when debugging an intelligent agent’s reasoning [6].”
ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models (2017, background): “As the complexity of machine learning algorithms increases, many researchers have recognized the importance of model interpretation and developed interactive tools to help users better understand them [9,13,21,24,33,37].”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “For example, user feedback may take the form of model constraints [18], critiques to the model’s search space [45], or adjustments to the model’s weights of evidence [26].”
Semantically Equivalent Adversarial Rules for Debugging NLP models (2018, background): “Previous work on debugging primarily focuses on explaining predictions in validation data in order to uncover bugs (Ribeiro et al., 2016, 2018; Kulesza et al., 2011), or find labeling errors (Zhang et al., 2018; Koh and Liang, 2017).”
Power to the People: The Role of Humans in Interactive Machine Learning (2014, background): “In a recent study, Kulesza et al. (2012) provided users of a content-based music recommender with a 15-minute tutorial discussing how the recommender worked and how the various feedback controls (e.”