{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Sentiment analysis of Guardian World News articles" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Get articles from a website" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Install rss parser dependency" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip3 install feedparser" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Parsing RSS feed for world news" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import feedparser\n", "feed_url = \"https://www.theguardian.com/world/rss\"\n", "feed = feedparser.parse(feed_url)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import re\n", "for item in feed.entries:\n", " # sanitize html\n", " item.description = re.sub('<[^<]+?>', '', item.description)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Install Vader Sentiment library and perform sentiment analysis" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip3 install vaderSentiment" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n", "analyser = SentimentIntensityAnalyzer()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "sentiment_results = []\n", "for item in feed.entries:\n", " sentiment_title = analyser.polarity_scores(item.title)\n", " sentiment_description = analyser.polarity_scores(item.description)\n", " sentiment_results.append([sentiment_title['compound'], sentiment_description['compound']])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Install Matplotlib and visualize compound score" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip3 install matplotlib" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "plt.rcParams['figure.figsize'] = (15, 3)\n", "plt.plot(sentiment_results, drawstyle='steps')\n", "plt.title('Sentiment analysis relationship between title and description (Guardian World News)')\n", "plt.legend(['title', 'description'])\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 4 }