Evolutionary optimization for ranking how-to questions based on user-generated contents

• Published in: Expert systems with applications Vol. 40; no. 17; pp. 7060 - 7068
• Main Authors: Atkinson, John, Figueroa, Alejandro, Andrade, Christian
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.12.2013; Elsevier
• Subjects: Algorithmics. Computability. Computer arithmetics; Applied sciences; Artificial intelligence; Clustering; Communities; Community question-answering; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Concept clustering; Evolutionary; Evolutionary computation; Exact sciences and technology; Expert systems; HPSG parsing; Optimization; Platforms; Question-answering systems; Ranking; Software; Speech and sound recognition and synthesis. Linguistics; Theoretical computing; User-generated content; Concept clustering; Community question-answering; Question-answering systems; HPSG parsing; Evolutionary computation; Electronic discussion group; User; Hierarchical classification; Evolutionary algorithm; Cluster; Syntactic analysis; Social network; Modeling; Information browsing; Semantics; World wide web; Verb; Content-based retrieval; Large scale; Internet; Responder
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2013.06.017

•We propose an evolutionary optimization model for ranking how-to questions from the web.•The approach combines evolutionary computation techniques and clustering methods.•Experiments show promising results of evolutionary optimization to generate correct HOW-TO answers. In this work, a new evolutionary model is proposed for ranking answers to non-factoid (how-to) questions in community question-answering platforms. The approach combines evolutionary computation techniques and clustering methods to effectively rate best answers from web-based user-generated contents, so as to generate new rankings of answers. Discovered clusters contain semantically related triplets representing question–answers pairs in terms of subject-verb-object, which is hypothesized to improve the ranking of candidate answers. Experiments were conducted using our evolutionary model and concept clustering operating on large-scale data extracted from Yahoo! Answers. Results show the promise of the approach to effectively discovering semantically similar questions and improving the ranking as compared to state-of-the-art methods.