{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:56:21Z","timestamp":1766580981140,"version":"3.48.0"},"reference-count":50,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This interdisciplinary pilot study examines the use of Natural Language Processing (NLP) techniques, specifically Large Language Models (LLMs) with Prompt Engineering (PE), to analyze economic vulnerability from qualitative self-narratives. Seventy narratives from twenty-five women in the Palk Bay coastal region of Rameshwaram, India were analyzed using a schema adapted from a contextual empowerment framework. The study operationalizes theoretical constructs into structured Information Extraction (IE) templates, enabling systematic identification of multiple vulnerability aspects, contributing factors, and experiential expressions. Prompt templates were iteratively refined and validated through dual-annotator review, achieving an F1-score of 0.78 on a held-out subset. Extracted elements were examined through downstream analysis, including pattern grouping and graph-based visualization, to reveal co-occurrence structures and recurring vulnerability configurations across narratives. The findings demonstrate that LLMs, when aligned with domain-specific conceptual models and supported by human-in-the-loop validation, can enable interpretable and replicable analysis of self-narratives. While findings are bounded by the pilot scale and community-specific context, the approach supports translation of narrative evidence into community-level program design and targeted grassroots outreach, with planned expansion to multi-site, multilingual datasets for broader applicability.<\/jats:p>","DOI":"10.3390\/bdcc10010006","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:22:27Z","timestamp":1766578947000},"page":"6","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Analyzing Vulnerability Through Narratives: A Prompt-Based NLP Framework for Information Extraction and Insight Generation"],"prefix":"10.3390","volume":"10","author":[{"given":"Aswathi","family":"Padmavilochanan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Clappana, Kollam 690525, India"},{"name":"Center for Women\u2019s Empowerment and Gender Equality, Amrita Vishwa Vidyapeetham, Amritapuri, Clappana, Kollam 690525, India"}]},{"given":"Veena","family":"Gangadharan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Applications, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Clappana, Kollam 690525, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9481-5248","authenticated-orcid":false,"given":"Tarek","family":"Rashed","sequence":"additional","affiliation":[{"name":"Geospatial Innovation Program, Center for Environment & Society, Washington College, Chestertown, MD 21620, USA"}]},{"given":"Amritha","family":"Natarajan","sequence":"additional","affiliation":[{"name":"Center for Women\u2019s Empowerment and Gender Equality, Amrita Vishwa Vidyapeetham, Amritapuri, Clappana, Kollam 690525, India"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, H., and Wang, W. (2022). Knowledge domain and emerging trends of social vulnerability research: A bibliometric analysis (1991\u20132021). Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph19148342"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1863598","DOI":"10.1080\/17482631.2020.1863598","article-title":"Vulnerable persons in society: An insider\u2019s perspective","volume":"16","author":"Numans","year":"2021","journal-title":"Int. J. Qual. Stud. Health-Well-Being"},{"key":"ref_3","first-page":"497","article-title":"Social vulnerability as an analytical lens for welfare state research: Concepts and typologies","volume":"36","author":"Zimmermann","year":"2017","journal-title":"Policy Soc."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100245","DOI":"10.1016\/j.wdp.2020.100245","article-title":"Vulnerability mapping: A conceptual framework towards a context-based approach to women\u2019s empowerment","volume":"20","author":"Gressel","year":"2020","journal-title":"World Dev. Perspect."},{"key":"ref_5","first-page":"3","article-title":"Qualitative social vulnerability assessments to natural hazards: Examples from coastal Thailand","volume":"14","author":"Massmann","year":"2014","journal-title":"J. Integr. Coast. Zone Manag."},{"key":"ref_6","unstructured":"UNDP International Center for Private Sector in Development\u2019s (ICPSD) SDG AI Lab (2024, February 20). Digital Social Vulnerability Index Technical Whitepaper. Available online: https:\/\/www.undp.org\/publications\/digital-social-vulnerability-index-technical-whitepaper."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kim, K., Kang, J.Y., and Hwang, C. (2025). Identifying Indicators Contributing to the Social Vulnerability Index via a Scoping Review. Land, 14.","DOI":"10.3390\/land14020263"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"104576","DOI":"10.1016\/j.ijdrr.2024.104576","article-title":"The origin and diffusion of the social vulnerability index (SoVI)","volume":"109","author":"Cutter","year":"2024","journal-title":"Int. J. Disaster Risk Reduct."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1719","DOI":"10.1007\/s10579-024-09766-4","article-title":"Perspectivist approaches to natural language processing: A survey","volume":"59","author":"Frenda","year":"2024","journal-title":"Lang. Resour. Eval."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/s41398-023-02592-2","article-title":"Natural language processing for mental health interventions: A systematic review and research framework","volume":"13","author":"Malgaroli","year":"2023","journal-title":"Transl. Psychiatry"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100654","DOI":"10.1016\/j.cosrev.2024.100654","article-title":"A survey on detecting mental disorders with natural language processing: Literature review, trends and challenges","volume":"53","year":"2024","journal-title":"Comput. Sci. Rev."},{"key":"ref_12","unstructured":"Keith, B., German, F., Krokos, E., Joseph, S., and North, C. (2025). Explainable AI Components for Narrative Map Extraction. arXiv."},{"key":"ref_13","unstructured":"German, F., Keith, B., and North, C. (2025). Narrative Trails: A Method for Coherent Storyline Extraction via Maximum Capacity Path Optimization. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jayaram, K., and Sangeeta, K. (2017, January 21\u201323). A review: Information extraction techniques from research papers. Proceedings of the 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Chennai, India.","DOI":"10.1109\/ICIMIA.2017.7975532"},{"key":"ref_15","first-page":"255","article-title":"Information extraction meets the semantic web: A survey","volume":"11","author":"Hogan","year":"2020","journal-title":"Semant. Web"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"101642","DOI":"10.1016\/j.giq.2021.101642","article-title":"Data-driven government: Cross-case comparison of data stewardship in data ecosystems","volume":"39","author":"Bharosa","year":"2022","journal-title":"Gov. Inf. Q."},{"key":"ref_17","unstructured":"Vatsal, S., and Dubey, H. (2024). A survey of prompt engineering methods in large language models for different nlp tasks. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"101575","DOI":"10.1109\/ACCESS.2022.3205314","article-title":"Computational understanding of narratives: A survey","volume":"10","author":"Ranade","year":"2022","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Piper, A., So, R.J., and Bamman, D. (2021, January 7\u201311). Narrative theory for computational narrative understanding. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic.","DOI":"10.18653\/v1\/2021.emnlp-main.26"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1609406919856797","DOI":"10.1177\/1609406919856797","article-title":"Transforming transcripts into stories: A multimethod approach to narrative analysis","volume":"18","author":"Nasheeda","year":"2019","journal-title":"Int. J. Qual. Methods"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.29333\/ajqr\/11456","article-title":"Insights on narrative analysis from a study of racial microaggressions and microaffirmations","volume":"6","author":"Bailey","year":"2021","journal-title":"Am. J. Qual. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1080\/21642850.2018.1515017","article-title":"Narrative analysis in health psychology: A guide for analysis","volume":"6","author":"Wong","year":"2018","journal-title":"Health Psychol. Behav. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1080\/12460125.2022.2074653","article-title":"Challenges in research data management practices: A literature analysis","volume":"31","author":"Birkbeck","year":"2022","journal-title":"J. Decis. Syst."},{"key":"ref_24","unstructured":"Bagchi, A. (2025, April 28). Challenges in Data Collection and Management for NGOs and How to Overcome Them. Vakilkaro. Available online: https:\/\/www.vakilkaro.com\/blogs\/challenges-in-data-collection-and-management-for-ngos\/."},{"key":"ref_25","unstructured":"Divyadarshini, S. (2024, February 21). Data-Driven Decision Making for Skilling NGOs: How MIS Can Transform Impact Measurement, EdZola. Available online: https:\/\/www.edzola.com\/post\/data-driven-decision-making-for-skilling-ngos-how-mis-can-transform-impact-measurement."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"8393","DOI":"10.1007\/s10462-022-10338-7","article-title":"A survey on narrative extraction from textual data","volume":"56","author":"Santana","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"46","DOI":"10.5530\/jscires.20251166","article-title":"Large Language Models in Biomedicine and Health: A Holistic Evaluation of the Effectiveness, Reliability and Ethics using Altmetrics","volume":"14","author":"Nedungadi","year":"2025","journal-title":"J. Scientometr. Res."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Amirova, A., Fteropoulli, T., Ahmed, N., Cowie, M.R., and Leibo, J.Z. (2024). Framework-based qualitative analysis of free responses of Large Language Models: Algorithmic fidelity. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0300024"},{"key":"ref_29","unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Xu, T., Wu, S., Diao, S., Liu, X., Wang, X., Chen, Y., and Gao, J. (2024, January 12\u201316). Sayself: Teaching llms to express confidence with self-reflective rationales. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA.","DOI":"10.18653\/v1\/2024.emnlp-main.343"},{"key":"ref_31","unstructured":"Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., and Brunskill, E. (2021). On the opportunities and risks of foundation models. arXiv."},{"key":"ref_32","unstructured":"Lynch, C.J., Jensen, E., Munro, M.H., Zamponi, V., Martinez, J., O\u2019Brien, K., Feldhaus, B., Smith, K., Reinhold, A.M., and Gore, R. (2024). GPT-4 Generated Narratives of Life Events using a Structured Narrative Prompt: A Validation Study. arXiv."},{"key":"ref_33","unstructured":"Matus, M., Urrutia, D., Meneses, C., and Keith, B. (2024, January 24). ROGER: Extracting Narratives Using Large Language Models from Robert Gerstmann\u2019s Historical Photo Archive of the Sacambaya Expedition in 1928. Proceedings of the Text2Story@ ECIR, Glasgow, Scotland."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gopal, L.S., Prabha, R., and Ramesh, M.V. (2022). Developing information extraction system for disaster impact factor retrieval from Web News Data. Information and Communication Technology for Competitive Strategies (ICTCS 2021) Intelligent Strategies for ICT, Springer Nature.","DOI":"10.1007\/978-981-19-0098-3_35"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Elfes, J. (2025). Mapping News Narratives Using LLMs and Narrative-Structured Text Embeddings. arXiv.","DOI":"10.1145\/3717867.3717868"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Su, H.T., Hsu, Y.C., Lin, X., Shi, X.Q., Niu, Y., Hsu, H.Y., Lee, H.Y., and Hsu, W. (2024, January 12\u201316). Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses. Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP, Miami, FL, USA.","DOI":"10.18653\/v1\/2024.findings-emnlp.872"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1162\/coli_a_00502","article-title":"Can large language models transform computational social science?","volume":"50","author":"Ziems","year":"2024","journal-title":"Comput. Linguist."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e2314021121","DOI":"10.1073\/pnas.2314021121","article-title":"Can Generative AI improve social science?","volume":"121","author":"Bail","year":"2024","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lim, S., and Schm\u00e4lzle, R. (2023). Artificial intelligence for health message generation: An empirical study using a large language model (LLM) and prompt engineering. Front. Commun., 8.","DOI":"10.3389\/fcomm.2023.1129082"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Yin, Z., Tyson, G., Haq, E.U., Lee, L.H., and Hui, P. (2024, January 13\u201317). Apt-pipe: A prompt-tuning tool for social data annotation using chatgpt. Proceedings of the ACM Web Conference 2024, Singapore.","DOI":"10.1145\/3589334.3645642"},{"key":"ref_41","unstructured":"Yang, Z., Li, L., Wang, J., Lin, K., Azarnasab, E., Ahmed, F., Liu, Z., Liu, C., Zeng, M., and Wang, L. (2023). Mm-react: Prompting chatgpt for multimodal reasoning and action. arXiv."},{"key":"ref_42","unstructured":"Ling, C., Zhao, X., Lu, J., Deng, C., Zheng, C., Wang, J., Chowdhury, T., Li, Y., Cui, H., and Zhang, X. (2024). Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Naveen, J.R., Ganesh, H.B., Kumar, M.A., and Soman, K.P. (2019). Distributed Representation of Healthcare Text Through Qualitative and Quantitative Analysis. Computer Aided Intervention and Diagnostics in Clinical and Medical Images, Springer.","DOI":"10.1007\/978-3-030-04061-1_23"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"100834","DOI":"10.1016\/j.ajogmf.2022.100834","article-title":"Identifying women with postdelivery posttraumatic stress disorder using natural language processing of personal childbirth narratives","volume":"5","author":"Bartal","year":"2023","journal-title":"Am. J. Obstet. Gynecol. MFM"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Calderon, N., Reichart, R., and Dror, R. (2025). The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs. arXiv.","DOI":"10.18653\/v1\/2025.acl-long.782"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, B., Huang, L., Beigi, A., Zhao, C., Tan, Z., Bhattacharjee, A., Jiang, Y., Chen, C., and Wu, T. (2024). From generation to judgment: Opportunities and challenges of llm-as-a-judge. arXiv.","DOI":"10.18653\/v1\/2025.emnlp-main.138"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Wang, L., Lyu, C., Ji, T., Zhang, Z., Yu, D., Shi, S., and Tu, Z. (2023, January 6\u201310). Document-Level Machine Translation with Large Language Models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, ACL Anthology, Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.1036"},{"key":"ref_48","unstructured":"Yamada, M. (2023, January 4\u20138). Optimizing Machine Translation through Prompt Engineering: An Investigation into ChatGPT\u2019s Customizability. Proceedings of the Machine Translation Summit XIX, Vol. 2: Users Track, Macau, China. Asia-Pacific Association for Machine Translation."},{"key":"ref_49","unstructured":"Muktadir, G.M. (2023). A brief history of prompt: Leveraging language models. (through advanced prompting). arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Xu, S., Zhao, K., Loney, J., Li, Z., and Visentin, A. (2025). Zero-Shot Image-Based Large Language Model Approach to Road Pavement Monitoring. arXiv.","DOI":"10.1111\/mice.70075"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/1\/6\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:52:33Z","timestamp":1766580753000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/1\/6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["bdcc10010006"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10010006","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,12,24]]}}}