--- title: FCV Data Mentions Explorer emoji: 📊 colorFrom: blue colorTo: indigo sdk: static pinned: false --- # FCV Data Mentions Explorer 📊 The **FCV Data Mentions Explorer** is an interactive, high-fidelity visual dashboard designed to explore and analyze validated dataset utilization across operational documents in **Fragile, Conflict, and Violence (FCV)**, forced displacement, and humanitarian contexts. This dashboard provides researchers, policy-makers, and funding agencies with a transparent lens into how data assets (microdata, household surveys, administrative registries) influence field operations and policy design. --- ## Key Features - **Interactive Word Cloud**: Scans the most popular and long-tail dataset entities. Clicking a dataset tag instantly filters the entire explorer workspace. - **Top Mined Data Mentions Rank**: Displays a distribution of dataset mentions across the corpus, using **document frequency deduplication** (counting at most once per document to avoid outlier skewing). - **Data Specificity Filtering**: Slice the entire dataset by specificity: - **Named Datasets** (e.g. *DHS Surveys*, *ZUS Registries*, *UNHCR PRIMES*) - *Default view* - **Descriptive Datasets** (e.g. *household surveys*, *national census*) - **Vague References** (e.g. *official data*, *local statistics*) - **Document Deep-Dive & PDF Viewer**: Jump directly into a report, browse paragraphs page-by-page (aligned with true PDF page numbers), and view the original context highlights. - **Downstream Impact Mapping**: Inspect the mapped *Downstream Impact Channels* (e.g. *Evidence*, *Citation*, *Monitoring*, *Design*) to see how data outputs directly translate into field actions. --- ## Methodology Brief FCV operational documents are heavily specialized and lack hand-labeled named entity recognition (NER) benchmarks. To build this dashboard, we introduce a semi-automated **Cascaded Candidate Generation and Verification** framework: - **Candidate Generation**: A local, lightweight model (**GLiNER2**), pre-trained on general research publications, performs high-recall token scanning over page-sized text chunks. - **Context-Aware Verification**: A frontier LLM (**GPT-4o**) serves as a context-aware judge under strict taxonomic guidelines, auditing candidate boundaries, verifying data-use validity, and mapping impact classifications. - **Fine-tuning Loop**: The verified corpus is used to fine-tune local models and power the explorer's database. --- # FCV Data Mentions Dashboard Manifest This directory contains the curated and validated data mentions extracted from Fragile, Conflict, and Violence (FCV), forced displacement, and refugee context documents. ## Folder Structure - `data/all_mined_data_mentions.csv`: Collated master spreadsheet of all validated mentions. - `data/validated/`: Validated documents in flat NER format. ## Curated Documents List (78 Unique Documents) | # | Document Name | Document Title | Corpus Category | Validated Mentions | |---|---|---|---|---| | 1 | `004_01_2021_r2p_report_on_resolution_767_eng` | participation in the programme | UNHCR / ReliefWeb / CIMP Reports | 1 | | 2 | `008_0349e1bab7009cf785257850006fa04c-full_report` | NEW ISSUES IN REFUGEE RESEARCH | UNHCR / ReliefWeb / CIMP Reports | 3 | | 3 | `010_BOSIB1554c314c0a2187c019d7e85bc2a91` | Kenya - Building Resilient and Responsive Health Systems Project | World Bank Project Appraisal Documents (PADs) | 20 | | 4 | `011_BOSIB12886229a02a1bcdc12ee681b5fe59` | South Sudan - Health Sector Transformation Project | SEIS / Other Humanitarian Briefs | 40 | | 5 | `012_04ffdb062b09d6fec12572720052760d-unhcr_dec2006` | NEW ISSUES IN REFUGEE RESEARCH | UNHCR / ReliefWeb / CIMP Reports | 1 | | 6 | `013_BOSIB0efb09b920d90858a0135df22da7d1` | Ethiopia - Digital ID for Inclusion and Services Project | World Bank Project Appraisal Documents (PADs) | 15 | | 7 | `014_07062015_bekaagovernorateprofile` | GENERAL OVERVIEW | UNHCR / ReliefWeb / CIMP Reports | 1 | | 8 | `014_BOSIB1dda1d49e0221807413cf06ea9ae3f` | Burundi - Jobs and Economic Transformation Project | UNHCR / ReliefWeb / CIMP Reports | 17 | | 9 | `015_08072015_northgovernorateprofile` | GENERAL OVERVIEW | UNHCR / ReliefWeb / CIMP Reports | 1 | | 10 | `018_10072015_akkargovernorateprofile` | GENERAL OVERVIEW | UNHCR / ReliefWeb / CIMP Reports | 2 | | 11 | `020_P1781250bdd2b50b0b9720d5c17632331c` | Azerbaijan - State and Peacebuilding Fund (SPF) : Improved Livelihoods for Internally Displaced Persons in Azerbaijan Project | World Bank Project Appraisal Documents (PADs) | 14 | | 12 | `021_108733-revised-public-wb-unhcr-policy-brief-final` | FRAGILITY AND POPULATION MOVEMENT IN AFGHANISTAN | UNHCR / ReliefWeb / CIMP Reports | 12 | | 13 | `023_Ethiopia-Second-Phase-Development-Response-to-Displacement-Impacts-Project-in-the-Horn-of-Africa-Project` | Ethiopia - Second Phase Development Response to Displacement Impacts Project in the Horn of Africa Project | World Bank Project Appraisal Documents (PADs) | 1 | | 14 | `024_Uganda-Generating-Growth-Opportunities-and-Productivity-for-Women-Enterprises-Uganda-Project` | Uganda - Generating Growth Opportunities and Productivity for Women Enterprises Uganda Project | World Bank Project Appraisal Documents (PADs) | 8 | | 15 | `025_1403-zaatarisafetysecurityreport2013-final` | !!!!!!! | SEIS / Other Humanitarian Briefs | 1 | | 16 | `027_14803f869ebccad5c125735c00572018-unhcr-aug2007` | How to Cope with a Refugee Shock ? Evidence from Uganda | UNHCR / ReliefWeb / CIMP Reports | 1 | | 17 | `027_Jordan-Emergency-Food-Security-Project` | Jordan - Emergency Food Security Project | World Bank Project Appraisal Documents (PADs) | 2 | | 18 | `030_1556029681unhcr_gsma_displaced_disconnected_-_connectivity_for_refugees_-_web` | CONNECTIVITY FOR REFUGEES | UNHCR / ReliefWeb / CIMP Reports | 7 | | 19 | `034_190415_gbv_secondary-data-analysis_cyclone-idai_moz_final` | Project Information Document-Integrated Safeguards Data Sheet - Equity with Quality and Learning at Secondary (EQUALS) - P164223 | UNHCR / ReliefWeb / CIMP Reports | 13 | | 20 | `035_1_advocacy_note_mineaction_-_niger_eng` | ADVOCACY NOTE A CRUCIAL NEED TO REINFORCE ACTIONS AGAINST THE GROWING THREAT OF EXPLOSIVE DEVICES (ED) IN NIGER | SEIS / Other Humanitarian Briefs | 5 | | 21 | `038_1e3fe15ddbc55d878525763800599cf8-unhcr_sep2009` | UNHCR policy on refugee protection and solutions in urban areas | UNHCR / ReliefWeb / CIMP Reports | 3 | | 22 | `040_Iraq-COVID-19-Vaccination-Project` | Iraq - COVID-19 Vaccination Project | World Bank Project Appraisal Documents (PADs) | 29 | | 23 | `046_20140519-south-sudan-protection-cluster-trends-analysis` | Protection Trends Analysis May 2014 | UNHCR / ReliefWeb / CIMP Reports | 2 | | 24 | `046_Cameroon-COVID-19-Preparedness-and-Response-Project` | Cameroon - COVID-19 Preparedness and Response Project | World Bank Project Appraisal Documents (PADs) | 2 | | 25 | `047_2014_afghanistan_refugee_and_returnee_overview` | The 2014 Afghanistan Refugee and Returnee Overview | UNHCR / ReliefWeb / CIMP Reports | 2 | | 26 | `051_2015-12-18_myt_web_embargoed` | INTRODUCTION | UNHCR / ReliefWeb / CIMP Reports | 3 | | 27 | `051_Pakistan-Balochistan-Human-Capital-Investment-Project` | Pakistan - Balochistan Human Capital Investment Project | World Bank Project Appraisal Documents (PADs) | 45 | | 28 | `054_Sudan-Basic-Education-Emergency-Support-Project` | Sudan - Basic Education Emergency Support Project | World Bank Project Appraisal Documents (PADs) | 22 | | 29 | `055_Chad-COVID-19-Response-Project` | Chad - COVID-19 Response Project | World Bank Project Appraisal Documents (PADs) | 7 | | 30 | `056_Niger-COVID-19-Emergency-Response-Project` | Niger - COVID-19 Emergency Response Project | World Bank Project Appraisal Documents (PADs) | 1 | | 31 | `060_Yemen-Emergency-COVID-19-Project` | Yemen - Emergency COVID-19 Project | World Bank Project Appraisal Documents (PADs) | 1 | | 32 | `061_Turkey-Formal-Employment-Creation-Project` | Turkey - Formal Employment Creation Project | World Bank Project Appraisal Documents (PADs) | 21 | | 33 | `062_Turkey-Municipal-Services-Improvement-Project` | Turkey - Municipal Services Improvement Project | World Bank Project Appraisal Documents (PADs) | 5 | | 34 | `069_Pakistan-Strengthening-Institutions-for-Refugee-Administration-Project` | Pakistan - Strengthening Institutions for Refugee Administration Project | World Bank Project Appraisal Documents (PADs) | 7 | | 35 | `06e584f33bd5a7c8f5d53001e2cd09f6c4e77019` | Developing value : the business case for sustainability in emerging markets | SEIS / Other Humanitarian Briefs | 2 | | 36 | `074_Djibouti-Integrated-Cash-Transfer-and-Human-Capital-Project` | Djibouti - Integrated Cash Transfer and Human Capital Project : Additional Financing | World Bank Project Appraisal Documents (PADs) | 2 | | 37 | `076_20200113_cimp_thematic_02_hudaydah_ceasefire` | CIVILIAN IMPACT MONITORING PROJECT | UNHCR / ReliefWeb / CIMP Reports | 1 | | 38 | `078_20200715_cimp_thematic_03_dwellings` | ■ Casualties from incidents impacting civilian houses ■ Casualties from incidents away from civilian houses | UNHCR / ReliefWeb / CIMP Reports | 1 | | 39 | `082_PAD2809-PAD-PUBLIC-disclosed-9-12-2018-IDA-R2018-0286-1` | Chad - AFRICA- P164748- Chad - Refugees and Host Communities Support Project - Procurement Plan | World Bank Project Appraisal Documents (PADs) | 5 | | 40 | `088_UGANDA-PAD-04272018` | Uganda - Support to Municipal Infrastructure Development Program Project : additional financing | World Bank Project Appraisal Documents (PADs) | 3 | | 41 | `0a42a3f1c22fed68d75a69de9feedd17ba1f2280` | On the Effects of Enforcement on Illegal Markets: Evidence from a Quasi-Experiment in Colombia* | SEIS / Other Humanitarian Briefs | 3 | | 42 | `0cf1e4d917c72425799848d588e618bb62107951` | The Economics of Sustainability : Causes and Consequences of Energy Market Transformation | SEIS / Other Humanitarian Briefs | 1 | | 43 | `100_Lebanon-Health-PAD-PAD2358-06152017` | مشروع تعزيز النظام الصحي في لبنان | World Bank Project Appraisal Documents (PADs) | 6 | | 44 | `107_PAD-Citizens-Charter-Afghanistan-P160567-Oct-7-Board-version-10072016` | P160567 - CCAP - AR | World Bank Project Appraisal Documents (PADs) | 7 | | 45 | `112_IDAR2016-0221-PAD-09012016` | الضفة الغربية وقطاع غزة - المدن المتكاملة ومشروع التنمية الحضرية | World Bank Project Appraisal Documents (PADs) | 7 | | 46 | `1143_zimbabwe_shona` | UNHCR Zimbabwe Stateless Shona Community Policy Brief | UNHCR / ReliefWeb / CIMP Reports | 8 | | 47 | `1165_brazil_protection_brief` | UNHCR Brazil Cash-Based Interventions Report | UNHCR / ReliefWeb / CIMP Reports | 2 | | 48 | `116_PAD1510-PAD-P152821-IDA-R2016-0078-1-Box394886B-OUO-9` | Africa - Displaced Persons and Border Communities Project | World Bank Project Appraisal Documents (PADs) | 2 | | 49 | `117_Somali-Urban-Investment-Planning-Project` | Somali - Urban Investment Planning Project | World Bank Project Appraisal Documents (PADs) | 13 | | 50 | `118_PAD1199-PAD-P144637-IDA-R2015-0247-1-Box393201B-OUO-9` | Cameroon - Third Phase of the Community Development Program Support Project | World Bank Project Appraisal Documents (PADs) | 7 | | 51 | `1268_rbsa_population_data` | UNHCR RBSA Southern Africa Population Data Analysis | SEIS / Other Humanitarian Briefs | 7 | | 52 | `1306_report_eng` | At a crossroads Unaccompanied and separated children in their transition to adulthood in Italy | SEIS / Other Humanitarian Briefs | 11 | | 53 | `136_PAD7230P1476890AD0October0100final` | The World Bank | World Bank Project Appraisal Documents (PADs) | 2 | | 54 | `1401_myanmar_durable_solutions` | UNHCR Myanmar Durable Solutions Report (2013) | UNHCR / ReliefWeb / CIMP Reports | 2 | | 55 | `140_779300PAD0P1280y0Box377377B00OUO090` | Burkina Faso - Electricity Sector Support Project (ESSP) | World Bank Project Appraisal Documents (PADs) | 13 | | 56 | `1530_indonesia_protection_brief` | UNHCR Indonesia Protection Brief | UNHCR / ReliefWeb / CIMP Reports | 1 | | 57 | `1577_venezuela_protection_cluster` | UNHCR Venezuela Protection Cluster Report (2023) | UNHCR / ReliefWeb / CIMP Reports | 2 | | 58 | `19a726d19f41f6513c0ed3091752ae113b543746` | Crop production, transport infrastructure, and agrobusiness nexus : evidence from Madagascar | World Bank Policy Research Working Papers (PRWPs) | 19 | | 59 | `1aae90deb505c7be16858e4101be5c1fcdfcb426` | Salt of the Earth | World Bank Policy Research Working Papers (PRWPs) | 36 | | 60 | `1b5681d8e07093a0d8585fead93fe7d9e844e21f` | T | World Bank Policy Research Working Papers (PRWPs) | 10 | | 61 | `4ca1fa7f7199d6fbe7ff3cdfc0f70d4f1d635579` | Will the clean development mechanism mobilize anticipated levels of mitigation ? | World Bank Policy Research Working Papers (PRWPs) | 6 | | 62 | `5678eb711d5b8019457808d11a4525a76c5fcc37` | The Role of Opinion Leaders in the Diffusion of New Knowledge: The Case of Integrated Pest Management | World Bank Policy Research Working Papers (PRWPs) | 3 | | 63 | `616_chad_rprf` | UNHCR Chad Regional Population Response Framework | UNHCR / ReliefWeb / CIMP Reports | 8 | | 64 | `777fa4790bc9880df0379956811e6625aa9a0b0e` | Growing together or growing apart? A village level study of the impact of the Doha round on rural China | World Bank Policy Research Working Papers (PRWPs) | 11 | | 65 | `782bb83b25a51b67205e6293a97e64528bb9b34f` | Trade costs, export development, and poverty in Rwanda | World Bank Policy Research Working Papers (PRWPs) | 13 | | 66 | `7b7a181a30a3e4aaa735d1acbabc3c26bbfc044f` | Long-term mitigation strategies and marginal abatement cost curves : a case study on Brazil | World Bank Policy Research Working Papers (PRWPs) | 6 | | 67 | `808_final_gbvims_2021_report_english` | 2021 | UNHCR / ReliefWeb / CIMP Reports | 2 | | 68 | `99cb9cc7265604e2fc594ac4573423a77424d952` | 销售的外部性和市场发展 | World Bank Policy Research Working Papers (PRWPs) | 3 | | 69 | `bf2312c5d35ec9c9ee30f3658d5465fd5ac744d3` | Shock waves : managing the impacts of climate change on poverty | World Bank Policy Research Working Papers (PRWPs) | 6 | | 70 | `c48720ecda01370f5bfdb64e9bb3ffa3e1fa4e71` | 帮助有生产能力但缺乏资产的农民取得成功:一个风险融资框架 | World Bank Policy Research Working Papers (PRWPs) | 5 | | 71 | `d53b6cd5243a095b705dec7c9309125ae50e643a` | PII: SO 169-5150(0 1 )00077 -9 | World Bank Policy Research Working Papers (PRWPs) | 14 | | 72 | `fae50f7b6ccef74c7b848d31782127b40857053d` | Implications for climate-change policy of research on cooperation in social dilemmas | World Bank Policy Research Working Papers (PRWPs) | 4 | | 73 | `ghana_gold_mining` | Gold Mining Spillovers in Ghana (Benshaul-Tolonen 2019) | SEIS / Other Humanitarian Briefs | 27 | | 74 | `helping_hands_ukraine` | Helping Hands: Ukrainian Refugee Integration Report | SEIS / Other Humanitarian Briefs | 10 | | 75 | `navigating_health_wellbeing` | Navigating Health & Well-being of Ukrainian Refugees (2024) | SEIS / Other Humanitarian Briefs | 10 | | 76 | `poland_economy` | UNHCR Poland Impact on Economy Report (2024) | SEIS / Other Humanitarian Briefs | 175 | | 77 | `seis_ukraine_2025` | UNHCR Ukraine Socio-Economic Inclusion (SEIS) Brief (2025) | SEIS / Other Humanitarian Briefs | 26 | | 78 | `somalia_baseline` | Somalia Solutions Pathways Baseline Analysis (2024) | UNHCR / ReliefWeb / CIMP Reports | 2 |