Spaces:
Build error
Build error
File size: 8,807 Bytes
6e97887 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/NaveenSanjaya/Right-Vote/blob/main/Social_Media_Sentiment.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"id": "296aa3df",
"metadata": {
"id": "296aa3df"
},
"source": [
"### Twitter Sentiment Analysis"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c9a7dc7a",
"metadata": {
"id": "c9a7dc7a"
},
"outputs": [],
"source": [
"import tweepy\n",
"import re\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"from transformers import AutoTokenizer, TFAutoModelForSequenceClassification\n",
"from scipy.special import softmax\n",
"\n",
"# Twitter API credentials\n",
"API_KEY = 'MCu2BiFyXXXXXXX'\n",
"API_SECRET_KEY = 'Cl8FYiqoVl82KyXXXXXXXXXX'\n",
"BEARER_TOKEN = 'AAAAAAAAAAAAAAAAAAAAXXXXXXX'\n",
"ACCESS_TOKEN = '1709435XXXXXXXX'\n",
"ACCESS_TOKEN_SECRET = 'Lp50yuMNJjg5SDZXXXXXXXX'\n",
"\n",
"# Set up Twitter API client\n",
"client = tweepy.Client(bearer_token=BEARER_TOKEN)\n",
"\n",
"# Initialize sentiment analysis model and tokenizer\n",
"roberta = \"cardiffnlp/twitter-roberta-base-sentiment\"\n",
"model = TFAutoModelForSequenceClassification.from_pretrained(roberta)\n",
"tokenizer = AutoTokenizer.from_pretrained(roberta)\n",
"\n",
"# Labels for sentiment analysis\n",
"labels = ['Negative', 'Neutral', 'Positive']\n",
"\n",
"def preprocess_tweet(tweet):\n",
" \"\"\"\n",
" Preprocess the tweet by replacing mentions and URLs with placeholders.\n",
" \"\"\"\n",
" tweet_words = []\n",
" for word in tweet.split(' '):\n",
" if word.startswith('@') and len(word) > 1:\n",
" word = '@user'\n",
" elif word.startswith('http'):\n",
" word = \"http\"\n",
" tweet_words.append(word)\n",
" return \" \".join(tweet_words)\n",
"\n",
"def fetch_tweets(query, max_results=100):\n",
" \"\"\"\n",
" Fetch recent tweets containing the specified query.\n",
" \"\"\"\n",
" tweet_data = []\n",
" try:\n",
" tweets = client.search_recent_tweets(query=query, max_results=max_results, tweet_fields=['created_at', 'text'])\n",
" if tweets.data:\n",
" for tweet in tweets.data:\n",
" tweet_data.append({\n",
" 'created_at': tweet.created_at,\n",
" 'text': tweet.text\n",
" })\n",
" except Exception as e:\n",
" print(f\"Error fetching tweets: {e}\")\n",
" return tweet_data\n",
"\n",
"def analyze_sentiment(text):\n",
" \"\"\"\n",
" Analyze the sentiment of the given text using the pre-trained model.\n",
" \"\"\"\n",
" tweet_proc = preprocess_tweet(text)\n",
" encoded_tweet = tokenizer(tweet_proc, return_tensors='tf')\n",
" output = model(**encoded_tweet)\n",
" scores = output[0][0].numpy()\n",
" scores = softmax(scores)\n",
" return dict(zip(labels, scores))\n",
"\n",
"def plot_sentiment_distribution(sentiment_counts):\n",
" \"\"\"\n",
" Plot a bar chart of sentiment distribution.\n",
" \"\"\"\n",
" sentiments = list(sentiment_counts.keys())\n",
" counts = list(sentiment_counts.values())\n",
" plt.bar(sentiments, counts, color=['red', 'gray', 'green'])\n",
" plt.xlabel('Sentiment')\n",
" plt.ylabel('Count')\n",
" plt.title('Sentiment Distribution')\n",
" plt.show()\n",
"\n",
"def main():\n",
" # Example candidate names\n",
" candidates = [\"Sajith Premadasa\", \"Ranil Wickremesinghe\", \"Anura Kumara\"]\n",
"\n",
" all_tweet_data = []\n",
"\n",
" for candidate in candidates:\n",
" print(f\"Fetching tweets for {candidate}...\")\n",
" tweets = fetch_tweets(candidate, max_results=100)\n",
" for tweet in tweets:\n",
" tweet['candidate'] = candidate\n",
" all_tweet_data.append(tweet)\n",
"\n",
" # Convert tweet data to DataFrame\n",
" df = pd.DataFrame(all_tweet_data)\n",
"\n",
" # Analyze sentiment for each tweet\n",
" sentiment_counts = {label: 0 for label in labels}\n",
"\n",
" for text in df['text']:\n",
" sentiment = analyze_sentiment(text)\n",
" for label, score in sentiment.items():\n",
" sentiment_counts[label] += score\n",
"\n",
" # Print sentiment distribution\n",
" print(\"Sentiment Distribution:\")\n",
" for label, count in sentiment_counts.items():\n",
" print(f\"{label}: {count}\")\n",
"\n",
" # Plot sentiment distribution\n",
" plot_sentiment_distribution(sentiment_counts)\n",
"\n",
"if __name__ == \"__main__\":\n",
" main()\n"
]
},
{
"cell_type": "markdown",
"id": "815021d8",
"metadata": {
"id": "815021d8"
},
"source": [
"### Facebook Sentiment Analysis"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cb529b29",
"metadata": {
"id": "cb529b29"
},
"outputs": [],
"source": [
"import requests\n",
"from transformers import pipeline\n",
"\n",
"# Facebook API credentials\n",
"ACCESS_TOKEN = 'EAAjjdeAxAF1eT5ZBbibXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX'\n",
"PAGE_ID = 'XXXXXXXXXXXXX'\n",
"\n",
"# Initialize sentiment analysis pipeline\n",
"sentiment_pipeline = pipeline('sentiment-analysis')\n",
"\n",
"def fetch_facebook_posts(page_id, access_token, limit=10):\n",
" \"\"\"\n",
" Fetch recent posts from a Facebook page.\n",
" \"\"\"\n",
" url = f'https://graph.facebook.com/{page_id}/posts'\n",
" params = {\n",
" 'access_token': access_token,\n",
" 'limit': limit,\n",
" }\n",
" response = requests.get(url, params=params)\n",
" response.raise_for_status()\n",
" return response.json().get('data', [])\n",
"\n",
"def analyze_sentiment(text):\n",
" \"\"\"\n",
" Analyze the sentiment of the given text using Hugging Face's sentiment analysis model.\n",
" \"\"\"\n",
" return sentiment_pipeline(text)\n",
"\n",
"def main():\n",
" # Fetch recent posts\n",
" posts = fetch_facebook_posts(PAGE_ID, ACCESS_TOKEN, limit=5)\n",
"\n",
" if not posts:\n",
" print(\"No posts found.\")\n",
" return\n",
"\n",
" # Analyze sentiment for each post\n",
" for post in posts:\n",
" post_message = post.get('message', '')\n",
" if post_message:\n",
" sentiment = analyze_sentiment(post_message)\n",
" print(f\"Post: {post_message}\")\n",
" print(f\"Sentiment: {sentiment[0]['label']} (Confidence: {sentiment[0]['score']:.2f})\")\n",
" print()\n",
"\n",
"if __name__ == \"__main__\":\n",
" main()\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.3"
},
"colab": {
"provenance": [],
"include_colab_link": true
}
},
"nbformat": 4,
"nbformat_minor": 5
} |