A research paper published by a team of computer scientists based at Indiana University and Portugal’s Instituto Gulbenkian de Ciencia have shed light on the possibility of “Computational fact checking from knowledge networks” to tackle issue of checking the growing volumes of data that is trafficked online.
The paper explains that a statement of fact is categorised into three parts : subject-predicate-object, e.g., (“Socrates,” “is a,” “person”). With such triples a knowledge graph is plotted, where nodes denote entities (i.e., subjects or objects of statements), and edges denote predicates.
“Given a set of statements that has been extracted from a knowledge repository, the resulting KG network represents all factual relations among entities mentioned in those statements. Given a new statement, we expect it to be true if it exists as an edge of the KG, or if there is a short path linking its subject to its object within the KG,”enunciates the paper.
For a statement that is infact misinformation, there would be neither edges nor short paths that connect subject and object.
Partially automated detection of various forms of misinformation do exist but with limitations. Automated reasoning methods are hampered by the inherent ambiguity of language and by deliberate deception. However, under certain conditions, reliable knowledge transmission can take place online, case in point, Wikipedia.
The paper outlines leveraging such online silos with reliable collection of factual human knowledge and run an automatic fact checking exercise based on the shortest path problem in graph theory.
Read more here.
(Image credit: Map of the Internet, via Wikimedia Commons)