AmiinBoss/Youtube_comment_analaysis

this project is about the comments we posted about trending topic in Somalia where Lieutenant(Taliye Qoslaaye) killed a business young man (Abuukar) # Somali Social Media Sentiment Analysis on a High-Profile Case This project analyzes Somali social media discussions surrounding the high-profile case of a police commander allegedly implicated in the murder of businessman Abuukar in the Heliwaa district. By leveraging data science and NLP techniques, the project aims to understand public sentiment, engagement patterns, and the broader societal implications reflected in online discourse. --- ## 📚 Project Overview * **Context:** The case has garnered significant public and media attention in Somalia, raising critical questions about law enforcement accountability, corruption, and public trust in institutions. * **Objective:** To collect, clean, and analyze Somali-language social media comments to reveal sentiment trends, engagement dynamics, and key discussion topics related to the incident. --- ## 🗂️ Dataset * **Source:** Extracted from public Somali social media platforms using APIs (details anonymized for privacy). * **Size:** 2,527 comments, 1,705 unique authors, no missing values. * **Fields:** * `author`: Username of the commenter (1,705 unique). * `date`: Timestamp in ISO 8601 format. * `comment`: The comment text. * `like_count`: Number of likes (range: 0–171). * `reply_count`: Number of replies (range: 0–27). * `comment_length`: Character count for each comment. * **Format:** CSV file, structured and ready for analysis. --- ## ⚙️ Data Pipeline 1. **Data Extraction:** * API-based collection focused on Somali-language content about politics/society. * Ensured compliance with ethical and privacy standards. 2. **Data Preparation:** * Removed duplicates, ensured no missing data. * Verified integrity and cleaned for analysis. * Automated scripts for reproducibility. 3. **Sentiment Annotation:** * Manual or semi-automated labeling as Positive ('wanaag'), Negative ('xumaan'), or Neutral ('dhexdhexaad'). * Special attention to Somali language nuances. --- ## 🔍 Exploratory Data Analysis & Visualizatio …