Abe-Alefew/LexiLink

The aim of this mini-project is to to analyze the text and phonemic similarities between the Afan Oromo and Somali languages by examining word frequency, overlap, and phonemic distribution. # **LexiLink: Exploring the Linguistic Connection Between Afan Oromo & Somali Languages** Welcome to **LexiLink**! This project is all about diving into the **textual and phonemic relationships** between the **Afan Oromo** and **Somali** languages. Using **Python**, it analyzes shared words, cleans and tokenizes text, removes stopwords, counts word frequencies, and converts graphemes to phonemes. ## **Why This Project?** Languages often share hidden patterns, especially those with historical and geographical ties. The goal of LexiLink is to explore these connections by: ✔️ Identifying **common words** between Afan Oromo & Somali ✔️ Analyzing their **phonemic structures** ✔️ Understanding their **linguistic similarities** through data ## 🛠 **How It Works** 1. **Extract & Clean** text samples by tokenization, lemmatization and removal of stopwords 2. **Compare & Analyze** shared words and **Do** G2P conversion 3. **Visualize** phoneme distributions ## 🚀 **Getting Started** ### **1. Clone the Repository** ```sh git clone github.com cd LexiLink ``` ### **2. Install Dependencies** ```sh pip install numpy matplotlib ``` ### 🔹 **Note:** - `re` and `collections` are **built-in Python modules**, so no installation is needed. - Ensure you have **Python installed** by running: ```sh python --version ``` - It’s recommended to use a virtual environment (`venv`) to keep dependencies organized. ### **3. Run the Analysis.** ```sh python lexi_link.py ``` ## 💡 **Who Can Use This?** Anyone interested in: 🔹 **Linguistics & Computational Analysis** 🔹 **Text Processing & NLP** 🔹 **African Language Studies** 🔹 **Phonetics & Language Comparisons** ## Dependencies ### This project depends on the following libraries: * collections * numpy * re * matplotlib ## 🚀 Future Advancements - **Expand Language Coverage** – Add more Cushitic and Afro-Asiatic languages. - **AI & NLP Integration** – Use machine learning for better lexical similarity detectio …