CoChat

Finding Streams in Knowledge Graphs to Support Fact Checking

Open access
Shiralkar, Prashant, Flammini, Alessandro, Menczer, Filippo, Ciampaglia, Giovanni Luca · 2017 · 2017 IEEE International Conference on Data Mining (ICDM)
Cited by 119

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Abstract

The volume of information generated online makes it impossible to manually fact-check all claims. Computational approaches for fact checking may be the key to help mitigate the risks of massive misinformation spread. Such approaches can be designed to not only be scalable and effective at assessing veracity of dubious claims, but also to boost a human fact checker's productivity by surfacing relevant facts and patterns to aid their analysis. We present a novel, unsupervised network-flow based approach to determine the truthfulness of a statement of fact expressed in the form of a triple. We view a knowledge graph of background information about real-world entities as a flow network, and show that computational fact checking then amounts to finding a "knowledge stream" connecting the subject and object of the triple. Evaluation on a range of real-world and hand-crafted datasets of facts reveals that this network-flow model can be very effective in discerning true statements from false ones, outperforming existing algorithms on many test cases. Moreover, the model is expressive in its ability to automatically discover several useful patterns and surface relevant facts that may help a human fact checker.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icdm.2017.105

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

  • A note on two problems in connexion with graphs

    Dijkstra, E. W. (1959) · Numerische Mathematik · doi:10.1007/bf01386390 · Cited by 29,065

  • Knowledge Graph Embedding by Translating on Hyperplanes

    Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8870 · Cited by 3,915 · cited 1×

    “On the other, there are statistical learning models (e.g., RESCAL [24], TransE [10], TransH [25], TransR [26], and ProjE [27]) that create vector embeddings for entities and relations, which can be used to assign similarity scores.”
    Background
  • Learning Entity and Relation Embeddings for Knowledge Graph Completion

    Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9491 · Cited by 3,749 · cited 1×

    “g., ILP [22] and AMIE [23]), which mine firstorder Horn clauses and are thus easy to interpret. On the other, there are statistical learning models (e.g., RESCAL [24], TransE [10], TransH [25], TransR [26], and ProjE [27]) that create vector embeddings for entities and relations, which can be used to assign similarity…”
    Background
  • Knowledge vault: a web-scale approach to probabilistic knowledge fusion

    Dong, X., Gabrilovich, E., Heitz, G., Horn, W., Lao, N., Murphy, K., Strohmann, T., Sun, S., & Zhang, W. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623623 · Cited by 1,533 · cited 1×

    “y Queen Orange Julius ! Peter Cundill Berkshire Hathaway Fig. 5. Relevant facts about a target claim as surfaced by Knowledge Stream. test cases [7], and in large-scale machine reading projects [28], [29]. They also offer some interpretability due to the features (or rules) they learn. Our methods achieve comparable o…”
    Method
  • Detection and Resolution of Rumours in Social Media: A Survey

    Zubiaga, A., Aker, A., Bontcheva, K., Liakata, M., & Procter, R. (2019) · ACM Computing Surveys · doi:10.1145/3161603 · Cited by 862 · cited 1×

    “To address these problems, numerous approaches have been designed to study and mitigate the effects of misinformation spread (see Zubiaga et al. [2]).”
    Background
  • Untitled work

    Ratkiewicz (2011) · doi:10.1145/1963192.1963301 · Cited by 541 · cited 1×

    “and other contextual indicators around entities of interest, e.g., characteristic features in user account metadata, unexpected shifts in temporal signals, credibility, and so on. For example, Truthy [17], Rumorlens [18], TweetCred [19], and ClaimBuster [20] are systems whose aim is to study the spread of misinformati…”
    Background
  • Computational Fact Checking from Knowledge Networks

    Ciampaglia, G. L., Shiralkar, P., Rocha, L. M., Bollen, J., Menczer, F., & Flammini, A. (2015) · PLOS ONE · doi:10.1371/journal.pone.0128193 · Cited by 486

    Self-citation

Cited by

See all 119

Metadata

Authors
Shiralkar, P., Flammini, A., Menczer, F., & Ciampaglia, G. L.
Venue
2017 IEEE International Conference on Data Mining (ICDM)
Publisher
IEEE
Published
2017-11
Pages
859-864
ISSN
1550-4786 (ISSN-L)
OpenAlex
W2748606298
Cited by
119
References
7
FWCI
50.38
Type
conference paper
Language
en
Open access
green

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.