{"type":"script","doc_desc":{"producers":[{"name":"Reproducibility WBG","abbr":"DECDI","affiliation":"World Bank - Development Impact Department","role":"Verification and preparation of metadata"}],"prod_date":"2025-12-05","version":"1"},"project_desc":{"authoring_entity":[{"name":"Martin Elias De Simone","affiliation":"World Bank","email":"mdesimone@worldbank.org"},{"name":"Federico Hernan Tiberti","affiliation":"World Bank","email":"ftiberti@worldbank.org"},{"name":"Maria Barron Rodriguez","affiliation":"World Bank","email":"mbarronrodriguez@worldbank.org"},{"name":"Federico Manolio","affiliation":"World Bank","email":"fmanolio@worldbank.org"},{"name":"Wuraola Mosuro","affiliation":"World Bank","email":"wmosuro@worldbank.org"},{"name":"Eliot Jolomi Dikoru","affiliation":"World Bank","email":"edikoru@worldbank.org"}],"title_statement":{"title":"Reproducibility package for From Chalkboards To Chatbots: Evaluating The Impact Of Generative Ai On Learning Outcomes In Nigeria","idno":"RR_NGA_2025_349"},"data_statement":"Data is forthcoming in the World Bank Microdata Library and included in the reproducibility package.","software":[{"name":"R","version":"4.5.1"}],"scripts":[{"title":"Reproducibility package for From Chalkboards To Chatbots: Evaluating The Impact Of Generative Ai On Learning Outcomes In Nigeria","date":"2025-12","notes":"Computational reproducibility verified by Development Impact (DECDI) Analytics team, World Bank.","instructions":"See README in reproducibility package.","file_name":"RR_NGA_2025_349","zip_package":"RR_NGA_2025_349.zip","dependencies":"R dependencies are listed in the file renv.lock."}],"repository_uri":[{"name":"Reproducible Research Repository (World Bank)","uri":"https:\/\/reproducibility.worldbank.org"}],"production_date":"2025-12-05","abstract":"This study evaluates the impact of a program leveraging large language models (LLMs) for virtual tutoring in secondary education in Nigeria. Using a randomized controlled trial, the program deployed Microsoft Copilot (powered by GPT-4) to support first-year senior secondary students in English language learning over six weeks. The intervention demonstrated significant improvements of 0.31 standard deviations on an assessment that included English topics aligned with the Nigerian curriculum, knowledge of artificial intelligence and digital skills. The effect on English, the main outcome of interest, was of 0.23 standard deviations. Cost-effectiveness analysis revealed substantial learning gains, equating to 1.5 to 2 years of 'business-as-usual' schooling, situating the intervention among some of the most cost-effective programs to improve learning outcomes. An analysis of heterogeneous effects shows that while the program benefits students across the baseline ability distribution, the largest effects are for female students, and those with higher initial academic performance. The findings highlight that AI-powered tutoring, when designed and used properly, can have transformative impacts in the education sector in low-resource settings.","geographic_units":[{"name":"Nigeria","code":"NGA"}],"keywords":[{"name":"Large-Language Models"},{"name":"Adaptive Learning"},{"name":"Artificial Intelligence"},{"name":"Education Technology"},{"name":"Secondary Education"},{"name":"Teaching At The Right Level"}],"topics":[{"id":"C93","uri":"https:\/\/www.aeaweb.org\/econlit\/jelCodes.php?view=jel","vocabulary":"Journal of Economic Literature (JEL)","name":"Field Experiments","parent_id":"C9"},{"id":" I21","uri":"https:\/\/www.aeaweb.org\/econlit\/jelCodes.php?view=jel","vocabulary":"Journal of Economic Literature (JEL)","name":"Analysis of Education","parent_id":"I2"},{"id":" J24","uri":"https:\/\/www.aeaweb.org\/econlit\/jelCodes.php?view=jel","vocabulary":"Journal of Economic Literature (JEL)","name":"Human Capital \u2022 Skills \u2022 Occupational Choice \u2022 Labor Productivity","parent_id":"J2"},{"id":" O15","uri":"https:\/\/www.aeaweb.org\/econlit\/jelCodes.php?view=jel","vocabulary":"Journal of Economic Literature (JEL)","name":"Human Resources \u2022 Human Development \u2022 Income Distribution \u2022 Migration","parent_id":"O1"},{"id":" O33","uri":"https:\/\/www.aeaweb.org\/econlit\/jelCodes.php?view=jel","vocabulary":"Journal of Economic Literature (JEL)","name":"Technological Change: Choices and Consequences \u2022 Diffusion Processes","parent_id":"O3"}],"output":[{"type":"Working Paper","description":"Policy Research Working Papers (PRWP) 11125","title":"From Chalkboards To Chatbots: Evaluating The Impact Of Generative Ai On Learning Outcomes In Nigeria","uri":" http:\/\/documents.worldbank.org\/curated\/en\/099548105192529324","doi":"https:\/\/doi.org\/10.1596\/1813-9450-11125","license":"CC BY 3.0 IGO","license_uri":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/igo\/"}],"language":[{"name":"English","code":"EN"}],"technology_requirements":"Runtime: 5 minutes","disclaimer":"The materials in the reproducibility packages are distributed as they were prepared by the staff of the International Bank for Reconstruction and Development\/The World Bank. The findings, interpretations, and conclusions expressed in this event do not necessarily reflect the views of the World Bank, the Executive Directors of the World Bank, or the governments they represent. The World Bank does not guarantee the accuracy of the materials included in the reproducibility package.","license":[{"name":"Modified BSD3","uri":"https:\/\/opensource.org\/license\/bsd-3-clause\/"}],"contacts":[{"name":"Martin Elias De Simone","affiliation":"World Bank","email":"mdesimone@worldbank.org"},{"name":"Reproducibility WBG","affiliation":"World Bank","email":"reproducibility@worldbank.org"}],"datasets":[{"name":"Data for From Chalkboards to Chatbots: Evaluating the Impact of Generative AI on Learning Outcomes in Nigeria","note":"Source: World Bank. Data was collected by the authors during May-July 2024. Data contains the school treatment\/control assignment, students' learning evaluations, and students' attendance and performance during regular classroom exams. A detailed and more documented version of this dataset is forthcoming in the World Bank Microdata Library.\nData files: \"assessment_with_key.csv\", \"attendance_clean.csv\", \"baseline_with_key.csv\", \"endline_with_key.csv\", \"list_tc.csv\", \"performance_score_merging_sheet.csv\".","access_type":"Data is forthcoming in the World Bank Microdata Library and included in the reproducibility package.","citation":"De Simone, Martin; Tiberti, Federico; Barron Rodriguez, Maria; Manolio, Federico; Mosuro, Wuraola; and Eliot J. Dikoru.\n2025.\n\"Data for From Chalkboards to Chatbots: Evaluating the Impact of Generative AI on Learning Outcomes in Nigeria [dataset]\".\nForthcoming in the World Bank Microdata Library."}],"reproduction_instructions":"1. Open the RStudio project file \"replication_package.Rproj\".\n2. Run the script \"main.R\".","technology_environment":"Paper exhibits were reproduced on a computer with the following specifications:\n\u2022 OS: Windows 11 Enterprise, version 24H2\n\u2022 Processor: Intel(R) Core(TM) Ultra 7 165U (2.10 GHz)\n\u2022 Memory available: 32.0 GB"},"tags":[{"tag":"DOI"},{"tag":"Open Code"},{"tag":"Open Data"}],"schematype":"script"}