The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index.
Explaining Data-Driven Document Classifications1
Abstract
Many document classification applications require human understanding of the reasons for data-driven classification decisions by managers, client-facing employees, and the technical team. Predictive models treat documents as data to be classified, and document data are characterized by very high dimensionality, often with tens of thousands to millions of variables (words). Unfortunately, due to the high dimensionality, understanding the decisions made by document classifiers is very difficult. This paper begins by extending the most relevant prior theoretical model of explanations for intelligent systems to account for some missing elements. The main theoretical contribution is the definition of a new sort of explanation as a minimal set of words (terms, generally), such that removing all words within this set from the document changes the predicted class from the class of interest. We present an algorithm to find such explanations, as well as a framework to assess such an algorithm’s performance. We demonstrate the value of the new approach with a case study from a real-world document classification task: classifying web pages as containing objectionable content, with the goal of allowing advertisers to choose not to have their ads appear on those pages. A second empirical demonstration on news-story topic classification shows the explanations to be concise and document-specific, and to be capable of providing understanding of the exact reasons for the classification decisions, of the workings of the classification models, and of the business application itself. We also illustrate how explaining the classifications of documents can help to improve data quality and model performance.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“All in all, counterfactual conditional statements are claimed to enable people to produce utterances that are factually false yet truthful irrespective of the interpretation adopted [32].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [32]
Citations
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
(1992) · Cited by 23,431
Neural networks for pattern recognition
Bishop, C. (1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,537
Fast algorithms for mining association rules
Agrawal, R., & Srikant, R. (1998) · Cited by 11,362
Design Science in Information Systems Research1
Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004) · MIS Quarterly · doi:10.2307/25148625 · Cited by 10,707 · cited 1×
“We now present an empirical case study (Hevner et al. 2004) onthe problem of classifying web pages as containing adult content.”
Libsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,123
Fast Algorithms for Mining Association Rules in Large Databases
Agrawal, R., & Srikant, R. (1994) · Very Large Data Bases · Cited by 9,454
Text categorization with Support Vector Machines: Learning with many relevant features
Joachims, T. (1998) · Lecture notes in computer science · doi:10.1007/bfb0026683 · Cited by 8,271
Research works printed but not linked: 2
- Buchanan, 1984, Rule Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project
- Hettich, S., and Bay, S. D. 1996. “The UCI KDD Archive” (https://kdd.ics.uci.edu).
Cited by
Sorted by citations
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
A Survey on the Explainability of Supervised Machine Learning
Burkart, N., & Huber, M. F. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12228 · Cited by 1,008
A data-driven approach to predict the success of bank telemarketing
Moro, S., Cortez, P. C., & Rita, P. (2014) · Decision Support Systems · doi:10.1016/j.dss.2014.03.001 · Cited by 976
Mittelstadt, B., Russell, C., & Wachter, S. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287574 · Cited by 794
Metadata
- Authors
- Martens, D., & Provost, F.
- Affiliations
- University of Antwerp (BE)
- New York University (US)
- Venue
- MIS Quarterly
- Publisher
- MIS Quarterly
- Published
- 2014-03-01
- Volume
- 38
- Issue
- 1
- Pages
- 73-100
- ISSN
- 0276-7783 (ISSN-L)
- 2162-9730
- OpenAlex
- W198744195
- Cited by
- 264
- References
- 68
- Citations by year
- 2026: 4 · 2025: 19 · 2024: 17 · 2023: 49 · 2022: 28 · 2021: 52 · 2020: 29 · 2019: 17 · 2018: 13 · 2017: 12 · 2016: 12 · 2015: 4 · 2014: 6
- FWCI
- 11.30
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- MIS Quarterly (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- explainable AI, document classification, high-dimensional text data, web page classification, model interpretability, data quality improvement
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
