Integrative Complexity Coding Raises Integratively Complex Issues

Bibliographic Data

ID6336702
AuthorsPhilip E Tetlock (0000-0002-6535-530X, University of Pennsylvania), Emlen Metz (0000-0001-5401-6508, University of Pennsylvania), S Emlen Metz (University of Pennsylvania), E Scott (0000-0002-8992-5936, University of Pennsylvania), Sydney E Scott (University of Pennsylvania), Peter Suedfeld (0000-0003-2563-036X, University of Pennsylvania)
Year2014
Volume35
Issue5
Pages625-634
Publication date2014-10-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenuePolitical Psychology (JOURNAL)
Journal identifiersISSN: 0162-895X • E-ISSN: 1467-9221
PublisherWiley (PUBLISHER • GB)
DOI10.1111/pops.12207
OpenAlexW1961166401
LanguageEN
Citations received15
References cited41

Conway, Conway, Gornick, and Houck (2014) report a major effort to automate integrative complexity coding. Judging this effort requires researchers to be more explicit in articulating key methodological assumptions about the coding process and theoretical assumptions about the construct. Unresolved issues include: (1) when, and on what basis, we should attribute divergences between human coders and algorithms to overestimations or underestimations by one or the other approach; and (2) to what extent second‐generation algorithms can yield Pareto improvements that reduce errors of both underestimation and overestimation. Further progress in developing natural language processing measures of this cognitive style will require sharper definitions of target constructs: in particular, different types of differentiation (dialectical and elaborative) and integration (hierarchical and flexible) and clearer guidelines for factoring context into assessments

Coding (social sciences · Cognitive science · Context (archaeology · Dialectic · Epistemology · Factoring · Statistics · Computer Science · Decision-Making and Behavioral Economics · Explainable Artificial Intelligence (XAI · Mathematics · Psychology · Topic Modeling · Theoretical Computer Science