README.md

roboswell · Mar 20, 2024 · acf8d53 · acf8d53
1 parent 3add052
commit acf8d53
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -13,23 +13,23 @@
 
 ### Portfolio Projects
 - GIS & Spatial Analysis:
- - Title: ["Examining Geospatial Covariate Relationships with Civilian Killings in South Sudan’s Civil War"](./GIS/GIS_covariate_relationships-killings-south_sudan.html)
+ - **Title:** ["Examining Geospatial Covariate Relationships with Civilian Killings in South Sudan’s Civil War"](./GIS/GIS_covariate_relationships-killings-south_sudan.html)
  - Focus: Geospatial Statistics
  Technology Used: QGIS, R, GeoDa
  - Contents: Geospatial interpolation, hot spot analysis, Moran's I calculation, Moran's I residual analysis, Lagrange Multiplier (LM) and Robust LM lag and error diagnostics, and Spatial Durbin models.
 - Data Visualization:
- - Title: **"UNAMID: Did the UN’s Withdrawal from Darfur Lead to More Violence against Civilians?"**
+ - **Title: "UNAMID: Did the UN’s Withdrawal from Darfur Lead to More Violence against Civilians?"**
  - [Version not showing code](./Data%20Viz-Darfur%20Violence%20as%20UN%20Left/visual_1-darfur_violence.html)
  - [Version showing all code](./Data%20Viz-Darfur%20Violence%20as%20UN%20Left/visual_1-darfur_violence-code_included.html)
  - Focus: GIS Mapping
  - Technology Used: R Markdown, ggmap, tmap, sp, sf, rgdal, stadia/stamen maps, plotly, dplyr, ggplot2, ggthemes, ggpubr, stringr, scales, and kableExtra
  - Contents: Interactive and static charts, GIS maps, heat map tables, density maps, and union buffers and using statistics within them
 - Natural Language Processing (NLP):
- - Title: ["Using News Articles on Events in Nigeria in 2019 to Predict Political Violence"](./ML-Predicting%20Violence%20with%20News/Using_Nigerian_News-based_ML_Models_to_Predict_Political_Violence.html)
+ - **Title:** ["Using News Articles on Events in Nigeria in 2019 to Predict Political Violence"](./ML-Predicting%20Violence%20with%20News/Using_Nigerian_News-based_ML_Models_to_Predict_Political_Violence.html)
  - Focus: NLP for Time-Series Forecasting
  - Technology Used: Python, TF-IDF word transformation, NLTK library, Scikit-Learn machine learning models, Scikit-Learn's TimeSeriesSplit, Augmented Dickey-Fuller Test, first-differencing, lags
  - Contents: Converting news articles by publishing date into time-series machine elarning forecasting models. Performance comparison between Ridge, Lasso, Random Forest, and XGBoost regression models
- - Title: **"LDA Topic Modeling & VADER Sentiment Analysis for Political News Articles on Events Related to Nigeria in 2019"**
+ - **Title: "LDA Topic Modeling & VADER Sentiment Analysis for Political News Articles on Events Related to Nigeria in 2019"**
  - [Primary document (Python)](./NLP-Topic%20Models%20&%20Sentiment/Nigeria_News_LDA_&_Sentiment_Analysis.html)
  - [Visualization for the project(R)](./NLP-Topic%20Models%20&%20Sentiment/Nigeria_News_Sentiment_Analysis-Viz-Created-in-R.html)
  - Focus: Topic Modeling & Sentiment Analysis