A hybrid approach to finding relevant social media content for complex domain specific information needs

Abstract

While contemporary semantic search systems offer to improve classical keyword-based search, they are not always adequate for complex domain specific information needs. The domain of prescription drug abuse, for example, requires knowledge of both ontological concepts and “intelligible constructs” not typically modeled in ontologies. These intelligible constructs convey essential information that include notions of intensity, frequency, interval, dosage and sentiments, which could be important to the holistic needs of the information seeker. In this paper, we present a hybrid approach to domain specific information retrieval that integrates ontology-driven query interpretation with synonym-based query expansion and domain specific rules, to facilitate search in social media on prescription drug abuse. Our framework is based on a context-free grammar (CFG) that defines the query language of constructs interpretable by the search system. The grammar provides two levels of semantic interpretation: 1) a top-level CFG that facilitates retrieval of diverse textual patterns, which belong to broad templates and 2) a low-level CFG that enables interpretation of specific expressions belonging to such textual patterns. These low-level expressions occur as concepts from four different categories of data: 1) ontological concepts, 2) concepts in lexicons (such as emotions and sentiments), 3) concepts in lexicons with only partial ontology representation, called lexico-ontology concepts (such as side effects and routes of administration (ROA)), and 4) domain specific expressions (such as date, time, interval, frequency and dosage) derived solely through rules. Our approach is embodied in a novel Semantic Web platform called PREDOSE, which provides search support for complex domain specific information needs in prescription drug abuse epidemiology. When applied to a corpus of over 1 million drug abuse-related web forum posts, our search framework proved effective in retrieving relevant documents when compared with three existing search systems.

Scaling Up Research on Drug Abuse and Addiction Through Social Media Big Data

“…For the data mining process, some studies developed and tested their own social media data monitoring and crawling systems. For example, Cameron and colleagues developed the Prescription Drug Abuse Online Surveillance and Epidemiology (PREDOSE) infrastructure to extract and analyze entities and sentiments of unstructured social media text data regarding prescription drug abuse [ 83 , 89 ]. Data collection periods varies across studies, ranging from 2 weeks to more than 1 year (eg, [ 7 , 36 ]).…”

“…With the exception of 2 studies conducted by Correia and colleagues [ 4 ], who used Instagram data, and Cameron and colleagues [ 83 ], who did not disclose the name of the analyzed social media platform, all other reviewed studies analyzed Twitter data. Also, with the exception of the Hanson et al study [ 2 ] that explored social networks, most of the reviewed studies examined the linguistic properties of Twitter communication data.…”

“…Among the reviewed studies, 4 reported that an institutional review board (IRB) approved their study [ 2 , 33 , 83 ]. Two studies reported that the IRB review was waived or was not applicable [ 7 , 36 ].…”

“…After screening a large number of searched articles within the PubMed database and the entire e-collection theme of “infodemiology and infoveillance” within the Journal of Medical Internet Research , we reviewed findings from 8 highly relevant studies that met all the inclusion criteria. We report empirical evidence from the studies in relation to the 4 research inquiries, the methodological and computational approaches, and ethical practices and considerations discussed in each study ( Multimedia Appendix 1 [ 2 , 4 , 7 , 33 , 36 , 83 - 85 ]).…”

Knowledge will propel machine understanding of content

“…(b) Example use of diverse knowledge and information extraction for deeper and more comprehensive understanding of text in health and drug abuse domain. See[5] for more information.…”