Constructing causal loop diagrams from large interview data sets

Newberry, Pablo; Carhart, Neil

doi:10.1002/sdr.1745

Cited by 10 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In specific research areas, the depth of qualitative text analysis extends beyond theme and pattern identification. For instance, in system dynamics, researchers engage in rigorous coding of textual data to discern model variables, causal links, and feedback loops (Kim & Andersen, 2012; Newberry & Carhart, 2023; Tomoaia‐Cotisel et al ., 2022). We revisited one of our prior studies, where interview data were analyzed to develop a causal loop diagram (CLD) (Jalali et al ., 2019).…”

Section: Introductionmentioning

confidence: 99%

Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

Jalali,

Akhavan

2024

System Dynamics Review

View full text Add to dashboard Cite

The recent advent of artificial intelligence (AI) language tools like ChatGPT has opened up new opportunities in qualitative research. We revisited a previous project on obesity prevention interventions, where we developed a causal loop diagram through in‐depth interview data analysis. Utilizing ChatGPT in our replication process, we compared its results against our original approach. We discuss that ChatGPT contributes to improved efficiency and unbiased data processing; however, it also reveals limitations in context understanding. Our findings suggest that AI language tools currently have great potential to serve as an augmentative tool rather than a replacement for the intricate analytical tasks performed by humans. With ongoing advancements, AI technologies may soon offer more substantial support in enhancing qualitative research capabilities, an area that deserves more investigation. © 2024 The Authors. System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.

show abstract

Section: Introductionmentioning

confidence: 99%

Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

Jalali,

Akhavan

2024

System Dynamics Review

View full text Add to dashboard Cite

show abstract

Systems Thinking, Causal Loop Diagram, and Systems Dynamic in Public Health Challenges: Navigating Long COVID Syndrome and Sense of Smell in LGBTQIA+ Communities

Akbari,

Wang,

Baghaei‐Yazdi

et al. 2024

Public Health Challenges

View full text Add to dashboard Cite

BackgroundThe coronavirus pandemic has profoundly affected global health, economic stability, and environmental sustainability. Despite these challenges, significant gaps in data remain, particularly in effectively assessing and engaging diverse communities such as color, LGBTQIA+ individuals, and low‐income groups. This shortage of comprehensive research limits our capacity to undertake sensitive studies, specifically in dealing with the complexities of long COVID, which some individuals continue to suffer from after their initial recovery.ObjectiveThis review delves into the ongoing repercussions of long‐term COVID‐19, a postinfectious syndrome marked by neurological symptoms such as cognitive deficits and sensory impairments, which may last well beyond the acute phase of the illness. These symptoms frequently overlap with mental health issues (e.g., anxiety and depression), which can aggravate the socioeconomic challenges faced by vulnerable populations, especially within the LGBTQA+ communities.MethodsTo tackle these complex interactions, we have introduced a novel public health framework: model‐based systems thinking (MBST), which incorporates System Dynamics and causal loop diagrams (CLD).Results and DiscussionThe articles were selected on the basis of their discussion of COVID‐19‐associated anosmia, exploration of olfactory dysfunction alongside neurocognitive disorders, and the challenges experienced in LGBQA+ communities. This approach offers a robust framework for dissecting the intricate ties between socioeconomic factors, health outcomes, and the extended recovery trajectories associated with long‐term COVID‐19, with a particular focus on olfactory dysfunction. We also explore strategies to make our models more accessible to healthcare providers and the LGBTQA+ communities, encouraging its broader adoption.ConclusionLong COVID's impact on public health and marginalized communities highlights the urgent need for adopting systems thinking models. Additionally, this article calls for a concerted effort from all experts to foster multidisciplinary, team‐based research and implement effective support measures for COVID‐19 survivors across all communities, mainly focusing on the scientific, social, and behavioral challenges LGBTQIA+ and low‐income individuals face.

show abstract

From text to map: a system dynamics bot for constructing causal loop diagrams

Hosseinichimeh,

Majumdar,

Williams

et al. 2024

System Dynamics Review

View full text Add to dashboard Cite

We introduce and test the System Dynamics Bot, a computer program leveraging a large language model to automate the creation of causal loop diagrams from textual data. To evaluate its performance, we ensembled two distinct databases. The first dataset includes 20 causal loop diagrams and associated texts sourced from the system dynamics literature. The second dataset comprises responses from 30 participants to a vignette, along with causal loop diagrams coded by three system dynamics modelers. The bot uses textual data and successfully identifies approximately 60% of the links between variables and feedback loops in both datasets. This article outlines our approach, provides examples, and presents evaluation results. We discuss encountered challenges and implemented solutions in developing the System Dynamics Bot. The bot can facilitate extracting mental models from textual data and improve model‐building processes. Moreover, the two datasets can serve as a test‐bed for similar programs. © 2024 The Author(s). System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.

show abstract

Constructing causal loop diagrams from large interview data sets

Cited by 10 publications

References 46 publications

Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

Systems Thinking, Causal Loop Diagram, and Systems Dynamic in Public Health Challenges: Navigating Long COVID Syndrome and Sense of Smell in LGBTQIA+ Communities

From text to map: a system dynamics bot for constructing causal loop diagrams

Contact Info

Product

Resources

About