Dataset Information

Topic models: a novel method for modeling couple and family text data.

ABSTRACT: Couple and family researchers often collect open-ended linguistic data-either through free-response questionnaire items, or transcripts of interviews or therapy sessions. Because participants' responses are not forced into a set number of categories, text-based data can be very rich and revealing of psychological processes. At the same time, it is highly unstructured and challenging to analyze. Within family psychology, analyzing text data typically means applying a coding system, which can quantify text data but also has several limitations, including the time needed for coding, difficulties with interrater reliability, and defining a priori what should be coded. The current article presents an alternative method for analyzing text data called topic models (Steyvers & Griffiths, 2006), which has not yet been applied within couple and family psychology. Topic models have similarities to factor analysis and cluster analysis in that they identify underlying clusters of words with semantic similarities (i.e., the "topics"). In the present article, a nontechnical introduction to topic models is provided, highlighting how these models can be used for text exploration and indexing (e.g., quickly locating text passages that share semantic meaning) and how output from topic models can be used to predict behavioral codes or other types of outcomes. Throughout the article, a collection of transcripts from a large couple-therapy trial (Christensen et al., 2004) is used as example data to highlight potential applications. Practical resources for learning more about topic models and how to apply them are discussed.

SUBMITTER: Atkins DC

PROVIDER: S-EPMC3468715 | biostudies-literature | 2012 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Topic models: a novel method for modeling couple and family text data.

Atkins David C DC Rubin Timothy N TN Steyvers Mark M Doeden Michelle A MA Baucom Brian R BR Christensen Andrew A

Journal of family psychology : JFP : journal of the Division of Family Psychology of the American Psychological Association (Division 43) 20120813 5

Couple and family researchers often collect open-ended linguistic data-either through free-response questionnaire items, or transcripts of interviews or therapy sessions. Because participants' responses are not forced into a set number of categories, text-based data can be very rich and revealing of psychological processes. At the same time, it is highly unstructured and challenging to analyze. Within family psychology, analyzing text data typically means applying a coding system, which can quan ...[more]

PMID: 22888778

Similar Datasets

Project description:BackgroundNovel consumer and lifestyle data, such as those collected by supermarket loyalty cards or mobile phone exercise tracking apps, offer numerous benefits for researchers seeking to understand diet- and exercise-related risk factors for diseases. However, limited research has addressed public attitudes toward linking these data with individual health records for research purposes. Data linkage, combining data from multiple sources, provides the opportunity to enhance preexisting data sets to gain new insights.ObjectiveThe aim of this study is to identify key barriers to data linkage and recommend safeguards and procedures that would encourage individuals to share such data for potential future research.MethodsThe LifeInfo Survey consulted the public on their attitudes toward sharing consumer and lifestyle data for research purposes. Where barriers to data sharing existed, participants provided unstructured survey responses detailing what would make them more likely to share data for linkage with their health records in the future. The topic modeling technique latent Dirichlet allocation was used to analyze these textual responses to uncover common thematic topics within the texts.ResultsParticipants provided responses related to sharing their store loyalty card data (n=2338) and health and fitness app data (n=1531). Key barriers to data sharing identified through topic modeling included data safety and security, personal privacy, requirements of further information, fear of data being accessed by others, problems with data accuracy, not understanding the reason for data linkage, and not using services that produce these data. We provide recommendations for addressing these issues to establish the best practice for future researchers interested in using these data.ConclusionsThis study formulates a large-scale consultation of public attitudes toward this kind of data linkage, which is an important first step in understanding and addressing barriers to participation in research using novel consumer and lifestyle data.

Project description:ObjectiveTo demonstrate how non-negative matrix factorization can be used to learn a temporal topic model over a large collection of primary care clinical notes, characterizing diverse COVID-19 pandemic effects on the physical/mental/social health of residents of Toronto, Canada.Materials and methodsThe study employs a retrospective open cohort design, consisting of 382,666 primary care progress notes from 44,828 patients, 54 physicians, and 12 clinics collected 01/01/2017 through 31/12/2020. Non-negative matrix factorization uncovers a meaningful latent topical structure permeating the corpus of primary care notes. The learned latent topical basis is transformed into a multivariate time series data structure. Time series methods and plots showcase the evolution/dynamics of learned topics over the study period and allow the identification of COVID-19 pandemic effects. We perform several post-hoc checks of model robustness to increase trust that descriptive/unsupervised inferences are stable over hyper-parameter configurations and/or data perturbations.ResultsTemporal topic modelling uncovers a myriad of pandemic-related effects from the expressive clinical text data. In terms of direct effects on patient-health, topics encoding respiratory disease symptoms display altered dynamics during the pandemic year. Further, the pandemic was associated with a multitude of indirect patient-level effects on topical domains representing mental health, sleep, social and familial dynamics, measurement of vitals/labs, uptake of prevention/screening maneuvers, and referrals to medical specialists. Finally, topic models capture changes in primary care practice patterns resulting from the pandemic, including changes in EMR documentation strategies and the uptake of telemedicine.ConclusionTemporal topic modelling applied to a large corpus of rich primary care clinical text data, can identify a meaningful topical/thematic summarization which can provide policymakers and public health stakeholders a passive, cost-effective, technology for understanding holistic impacts of the COVID-19 pandemic on the primary healthcare system and community/public-health.

Dataset Information

Topic models: a novel method for modeling couple and family text data.

Publications

Topic models: a novel method for modeling couple and family text data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets