國立虎尾科技大學 |

Computational Fact Checking by Mining Knowledge Graphs.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Computational Fact Checking by Mining Knowledge Graphs./
Author:	Shiralkar, Prashant.
Description:	1 online resource (193 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.
Contained By:	Dissertation Abstracts International79-02B(E).
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780355246513

Computational Fact Checking by Mining Knowledge Graphs.
Shiralkar, Prashant.

Computational Fact Checking by Mining Knowledge Graphs. - 1 online resource (193 pages)

Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

Misinformation and rumors have become rampant on online social platforms with adverse consequences for the real world. Fact-checking efforts are needed to mitigate the risks associated with the spread of digital misinformation. However, the pace at which information is generated online limits the capacity to fact-check claims at the same rate using current journalistic practices. Computational approaches may be a key for achieving scalable fact checking. To this end, this dissertation introduces network science and machine learning methods for fact checking by leveraging information in large knowledge bases, commonly known as knowledge graphs (KGs).

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355246513Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Computational Fact Checking by Mining Knowledge Graphs.
LDR:03327ntm a2200385Ki 4500 001 909037
005 20180419104825.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355246513
035 $a (MiAaPQ)AAI10623583
035 $a (MiAaPQ)indiana:14922
035 $a AAI10623583
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Shiralkar, Prashant. $3 1179536
245 1 0 $a Computational Fact Checking by Mining Knowledge Graphs.
264 0 $c 2017
300 $a 1 online resource (193 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.
500 $a Adviser: Filippo Menczer.
502 $a Thesis (Ph.D.) $c Indiana University $d 2017.
504 $a Includes bibliographical references
520 $a Misinformation and rumors have become rampant on online social platforms with adverse consequences for the real world. Fact-checking efforts are needed to mitigate the risks associated with the spread of digital misinformation. However, the pace at which information is generated online limits the capacity to fact-check claims at the same rate using current journalistic practices. Computational approaches may be a key for achieving scalable fact checking. To this end, this dissertation introduces network science and machine learning methods for fact checking by leveraging information in large knowledge bases, commonly known as knowledge graphs (KGs).
520 $a We consider two variations of the fact-checking task. The first consists in assessing the truthfulness of a statement of fact as simple as a (subject, predicate, object) triple, where the subject entity is related to the object entity by the predicate relation. We show that a broad class of triples pertaining to generic relationships among entities in the real world, e.g., (Indianapolis, capitalOf, Indiana), can be checked effectively by finding a shortest path connecting their subject and object entities in the KG under appropriately designed semantic proximity metrics. We also extend this approach by considering multiple paths, following ideas from network flow theory. Evaluation on a range of facts related to entertainment, sports and more reveals that our methods are effective in discerning true statements from false ones, often outperforming state-of-the-art algorithms.
520 $a The second task consists in computing a relevance score that expresses the degree to which a person is associated with different professions or nationalities. For example, we wish to determine which of Scientist, Philosopher or Writer best describes Aristotle. We introduce a supervised learning approach for assessing such relevance by extracting useful features from the KG. Results show that our approach is effective, despite the limited information in the graph.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
650 4 $a Information technology. $3 559429
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
690 $a 0489
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Indiana University. $b Computer Sciences. $3 1179305
773 0 $t Dissertation Abstracts International $g 79-02B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10623583 $z click for full text (PQDT)