Tapping the power of text mining
Abstract
Sifting through vast collections of unstructured or semistructured data beyond the reach of data mining tools, text mining tracks information sources, links isolated concepts in distant documents, maps relationships between activities, and helps answer questions.
Integrity signals
Registry
Cites
Statistics
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?
Transformer-based language models have a great advantage over earlier text-summarization algorithms, which struggled to understand sentiment and meaning in textual data.
“This gives them a great advantage over earlier text-summarization algorithms, which struggled to understand sentiment and meaning in textual data (Fan et al., 2006).”
From Augmenting human innovation teams with artificial intelligence: Exploring transformer-based language models (2023) · cites this paper as Fan et al., 2006
The citation lists haven’t been fetched yet
References 6 · Cited by 433
- Authors
- Fan, W., Wallace, L., Rich, S., & Zhang, Z.
- Affiliations
- Virginia Tech (US)
- University of Connecticut (US)
- Venue
- Communications of the ACM
- Published
- 2006-09
- Volume
- 49
- Issue
- 9
- Pages
- 76-82
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2035716223
- Cited by
- 433
- References
- 6
- Citations by year
- 2026: 2 · 2025: 26 · 2024: 15 · 2023: 31 · 2022: 33 · 2021: 19 · 2020: 34 · 2019: 39 · 2018: 23 · 2017: 23 · 2016: 20 · 2015: 18 · 2014: 29 · 2013: 14 · 2012: 20
- FWCI
- 112.08
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Communications of the ACM (publishedVersion)
- UCLA - Biblioteca de Ciencias y Tecnologia Felix Morales Bueno (submittedVersion)
- Topics
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Data Mining
- Keywords
- text mining, unstructured data, semi-structured data, concept linking, relationship mapping, question answering
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
