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
Design science in information systems research
(2004) · Journal of the Association for Information Systems · doi:10.5555/2017212.2017217 · Cited by 8,254
Opinion Mining and Sentiment Analysis
Pang, B., & Lee, L. (2008) · now publishers, Inc. eBooks · doi:10.1561/9781601981516 · Cited by 6,957
LIBLINEAR: A Library for Large Linear Classification
Fan, R.-E., Chang, K., Hsieh, C., Xiang-rui, W., & Lin, C. (2008) · doi:10.5555/1390681.1442794 · Cited by 6,684
Opinion mining and sentiment analysis
Pang, B., & Lee, L. (2008) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000011 · Cited by 6,372
Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
Platt, J. C. (1999) · Cited by 4,834
From data mining to knowledge discovery: an overview
Fayyad, U. M., Piatetsky-Shapiro, G., & Smyth, P. (1996) · Knowledge Discovery and Data Mining · Cited by 2,395
BoosTexter: A Boosting-based System for Text Categorization
Schapire, R. E., & Singer, Y. (2000) · Machine Learning · doi:10.1023/a:1007649029923 · Cited by 2,191
NewsWeeder: Learning to Filter Netnews
Lang, K. (1995) · Elsevier eBooks · doi:10.1016/b978-1-55860-377-6.50048-7 · Cited by 2,119
Predictive Analytics in Information Systems Research1
Shmueli, G., & Koppius, O. R. (2011) · MIS Quarterly · doi:10.2307/23042796 · Cited by 1,328
Lessmann, S., Baesens, B., Mues, C., & Pietsch, S. (2008) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2008.35 · Cited by 1,231
Get another label? improving data quality and data mining using multiple, noisy labelers
Sheng, V. S., Provost, F. J., & Ipeirotis, P. G. (2008) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1401890.1401965 · Cited by 1,205
Self-citationMapping authors in intellectual space: A technical overview
McCain, K. W. (1990) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(199009)41:6 · Cited by 987
Andreas Hotho, A., Nürnberger, A., & Paaß, G. (2005) · LDV-Forum/Journal for language technology and computational linguistics · doi:10.21248/jlcl.20.2005.68 · Cited by 909
Benchmarking state-of-the-art classification algorithms for credit scoring
Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003) · Journal of the Operational Research Society · doi:10.1057/palgrave.jors.2601545 · Cited by 904
Fawcett, T. E., & Provost, F. J. (1997) · Data Mining and Knowledge Discovery · doi:10.1023/a:1009700419189 · Cited by 889
Self-citationText mining techniques for patent analysis
Tseng, Y., Lin, C.-J., & Lin, Y.-I. (2007) · Information Processing & Management · doi:10.1016/j.ipm.2006.11.011 · Cited by 784
Predictive Analytics in Information Systems Research
Shmueli, G., & Koppius, O. (2010) · doi:10.2139/ssrn.1606674 · Cited by 676
Extracting Tree-Structured Representations of Trained Networks
Craven, M. W., & SHAVLIK, J. W. (1995) · neural information processing systems · Cited by 602
Buchanan, B. G., & Shortliffe, E. H. (1984) · Cited by 577
An Efficient Explanation of Individual Classifications using Game Theory
Štrumbelj, E., & Kononenko, I. (2010) · Repository of the University of Ljubljana (University of Ljubljana) · doi:10.5555/1756006.1756007 · Cited by 570
Explanations From Intelligent Systems: Theoretical Foundations and Implications for Practice1
Gregor, S., & Benbasat, I. (1999) · MIS Quarterly · doi:10.2307/249487 · Cited by 535
Interpersonal Conflict and Its Management in Information System Development1
Barki, H., & Hartwick, J. (2001) · MIS Quarterly · doi:10.2307/3250929 · Cited by 498
Comprehensible credit scoring models using rule extraction from support vector machines
Martens, D., Baesens, B., Van Gestel, T., & Vanthienen, J. (2007) · European Journal of Operational Research · doi:10.1016/j.ejor.2006.04.051 · Cited by 448
Self-citationQi, X., & Davison, B. D. (2009) · ACM Computing Surveys · doi:10.1145/1459352.1459357 · Cited by 444
Uncovering the intellectual core of the information systems discipline
Sidorova, A., Evangelopoulos, N. E., Valacich, J. S., & Ramakrishnan, T. (2008) · Journal of the Association for Information Systems · doi:10.5555/2017388.2017390 · Cited by 425
Cognitive biases and decision support systems development: a design science approach
Arnott, D. R. (2005) · Information Systems Journal · doi:10.1111/j.1365-2575.2006.00208.x · Cited by 369
Uncovering the Intellectual Core of the Information Systems Discipline1
Sidorova, A., Evangelopoulos, N. E., Valacich, J. S., & Ramakrishnan, T. (2008) · MIS Quarterly · doi:10.2307/25148852 · Cited by 368
Text Categorization Using Weight Adjusted k-Nearest Neighbor Classification
Han, E.-H. S., Karypis, G., & Kumar, V. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45357-1_9 · Cited by 357
Semi-automated screening of biomedical citations for systematic reviews
Wallace, B. C., Trikalinos, T. A., Lau, J., Brodley, C., & Schmid, C. H. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-55 · Cited by 351
Evaluating the Impact of DSS, Cognitive Effort, and Incentives on Strategy Selection
Todd, P., & Benbasat, I. (1999) · Information Systems Research · doi:10.1287/isre.10.4.356 · Cited by 312
The Impact of Explanation Facilities on User Acceptance of Expert Systems Advice
Ye, L. R., & Johnson, P. E. (1995) · MIS Quarterly · doi:10.2307/249686 · Cited by 290
Banker, R. D., & Kauffman, R. J. (2004) · Management Science · doi:10.1287/mnsc.1040.0206 · Cited by 264
Explaining Classifications For Individual Instances
Robnik‐Šikonja, M., & Kononenko, I. (2008) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2007.190734 · Cited by 255
Decisional Guidance for Computer-Based Decision Support1
Silver, M. S. (1991) · MIS Quarterly · doi:10.2307/249441 · Cited by 212
OPUS: An Efficient Admissible Algorithm for Unordered Search
Webb, G. I. (1995) · Journal of Artificial Intelligence Research · doi:10.1613/jair.227 · Cited by 207
Document-Word Co-regularization for Semi-supervised Sentiment Analysis
Sindhwani, V., & Melville, P. (2008) · Proceedings · doi:10.1109/icdm.2008.113 · Cited by 184
Arnol'd, �. �., Clark, Collier, P. A., Leech, & Sutton, S. G. (2006) · MIS Quarterly · doi:10.2307/25148718 · Cited by 166
Expectancy Theory as an Explanation of Voluntary Use of a Decision-Support System
Sanctis, G. D. (1983) · Psychological Reports · doi:10.2466/pr0.1983.52.1.247 · Cited by 163
Multiattribute Data Presentation and Human Judgment: A Cognitive Fit Perspective
Umanath, N. S., & Vessey, I. (1994) · Decision Sciences · doi:10.1111/j.1540-5915.1994.tb01870.x · Cited by 146
Sambamurthy, V., & Poole, M. S. (1992) · Information Systems Research · doi:10.1287/isre.3.3.224 · Cited by 144
Pant, G., & Srinivasan, P. (2005) · ACM Transactions on Information Systems · doi:10.1145/1095872.1095875 · Cited by 139
Providing Decisional Guidance for Multicriteria Decision Making in Groups
Limayem, M., & Desanctis, G. L. (2000) · Information Systems Research · doi:10.1287/isre.11.4.386.11874 · Cited by 139
Explaining instance classifications with interactions of subsets of feature values
Štrumbelj, E., Kononenko, I., & Robnik-Sikonja, M. (2009) · Data & Knowledge Engineering · doi:10.1016/j.datak.2009.01.004 · Cited by 129
How Incorporating Feedback Mechanisms in a DSS Affects DSS Evaluations
Kayandé, U., Bruyn, A. D., Lilien, G. L., Rangaswamy, A., & van Bruggen, G. H. (2008) · Information Systems Research · doi:10.1287/isre.1080.0198 · Cited by 125
DSS Effectiveness in Marketing Resource Allocation Decisions: Reality vs. Perception
Lilien, G. L., Rangaswamy, A., van Bruggen, G. H., & Starke, K. (2004) · Information Systems Research · doi:10.1287/isre.1040.0026 · Cited by 120
Audience selection for on-line brand advertising
Provost, F. J., Dalessandro, B., Hook, R., Zhang, X., & Murray, A. T. (2009) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1557019.1557098 · Cited by 118
Self-citationThe effects of structural characteristics of explanations on use of a DSS
Gonul, M. S., Önkal, D., & Lawrence, M. J. (2006) · Decision Support Systems · doi:10.1016/j.dss.2005.12.003 · Cited by 103
Why label when you can search?
Attenberg, J., & Provost, F. J. (2010) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1835804.1835859 · Cited by 75
Self-citationOn Chomsky and the Two Cultures of Statistical Learning
Norvig, P. (2017) · Springer eBooks · doi:10.1007/978-3-658-12153-2_3 · Cited by 70
Beat the machine: Challenging workers to find the unknown unknowns
Attenberg, J., Ipeirotis, P. G., & Provost, F. J. (2011) · Cited by 57
Self-citationHow to Explain Individual Classification Decisions
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1859912 · Cited by 54
The cost-minimizing inverse classification problem: a genetic algorithm approach
Mannino, M. V., & Koushik, M. V. (2000) · Decision Support Systems · doi:10.1016/s0167-9236(00)00077-4 · Cited by 47
Collaborative Email-Spam Filtering with the Hashing-Trick
Attenberg, J., Weinberger, K. Q., Dasgupta, A., Smola, A. J., & Zinkevich, M. (2009) · Cited by 46
Design principles of massive, robust prediction systems
Raeder, T., Stitelman, O., Dalessandro, B., Perlich, C., & Provost, F. J. (2012) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2339530.2339740 · Cited by 32
Self-citationAudience Selection for On-Line Brand Advertising: Privacy-Friendly Social Network TargetingPreprint
Provost, F. J., Dalessandro, B., Hook, R., Zhang, X., & Murray, A. T. (2011) · SSRN Electronic Journal · doi:10.2139/ssrn.1852644 · Cited by 26
Self-citationPseudo-social network targeting from consumer transaction data
Martens, D., & Provost, F. J. (2011) · Faculty Digital Archive (New York University Florence) · Cited by 22
Self-citationHägerstrand, A. (2011) · Cited by 5
Improved Algorithms for Document Classification &Query-based Multi-Document Summarization
D’Silva, S., Joshi, N., Rao, S., Venkatraman, S., & Shrawne, S. C. (2011) · International Journal of Engineering and Technology · doi:10.7763/ijet.2011.v3.261 · Cited by 4
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
