Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

MUMHEALTHMOBILEAPPS/Maternal_Health_Outcome

Domain:

healthcarenatural language processing

Record type:

dataset
Creator:
MUM
Host:
This data analysis project is a collaboration between HelpMum Africa and Data Science for Social Good (DSSG) in the USA. # Processing and Analyzing Data on Maternal Health Outcomes in Nigeria This data analysis project is a collaboration between HelpMum Africa and Data Science for Social Good (DSSG) in the USA. ## Code Contributors - Olayile Ejekwu: GitHub Profile - Talia Bird: GitHub Profile - Uzma Iffat: GitHub Profile ## Project Overview The primary objective of this project is to analyze data collected from traditional birth attendants across Nigeria. The data encompasses responses from 203 maternity homes, each of which answered a set of 6 open-ended questions. ## Methodology ### Data Collection The data was gathered through surveys conducted with traditional birth attendants across various maternity homes in Nigeria. These surveys aimed to capture detailed and qualitative insights into maternal health outcomes. ### Data Cleaning and Structuring Given the open-ended nature of the survey responses, rigorous data cleaning and structuring efforts were essential. This process involved: 1. **Removing Duplicates**: Ensuring that each response is unique and free from repetitions. 2. **Handling Missing Data**: Addressing incomplete responses to maintain data integrity. 3. **Standardizing Formats**: Ensuring consistency in the data format for better analysis. ### Natural Language Processing (NLP) Techniques To extract meaningful insights from the raw responses, classic NLP techniques were employed: 1. **Tokenization**: Breaking down text into individual words or phrases. 2. **Stop Words Removal**: Eliminating common words that do not contribute significant meaning. 3. **Stemming and Lemmatization**: Reducing words to their base or root forms. 4. **Sentiment Analysis**: Determining the sentiment expressed in the responses. 5. **Topic Modeling**: Identifying common themes and topics within the data. ## Insights and Findings The application of these techniques led to the extraction of valuable insights regarding maternal health outcomes. These findings are intended to inform …

Visit

github.com