File size: 5,440 Bytes
706fc89 7ddff49 c536f05 706fc89 c536f05 706fc89 7ddff49 706fc89 c536f05 706fc89 c536f05 706fc89 c536f05 706fc89 c536f05 706fc89 7ddff49 706fc89 7ddff49 706fc89 7ddff49 706fc89 c536f05 7ddff49 706fc89 7ddff49 |
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 |
import streamlit as st
import re
from langdetect import detect
from transformers import pipeline
import nltk
from docx import Document
import io
# Download required NLTK resources
nltk.download('punkt')
# Load AI models once to optimize performance
tone_model = pipeline("zero-shot-classification", model="facebook/roberta-large-mnli")
frame_model = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
# Updated tone categories
tone_categories = [
"Emotional & Urgent", "Harsh & Critical", "Negative & Somber",
"Empowering & Motivational", "Neutral & Informative", "Hopeful & Positive"
]
# Updated frame categories
frame_categories = [
"Human Rights & Justice", "Political & State Accountability", "Gender & Patriarchy",
"Religious Freedom & Persecution", "Grassroots Mobilization", "Environmental Crisis & Activism",
"Anti-Extremism & Anti-Violence", "Social Inequality & Economic Disparities"
]
# Detect language
def detect_language(text):
try:
return detect(text)
except Exception:
return "unknown"
# Analyze tone using RoBERTa model
def analyze_tone(text):
model_result = tone_model(text, candidate_labels=tone_categories)
return model_result["labels"][:2] # Top 2 tone labels
# Extract frames using BART model
def extract_frames(text):
model_result = frame_model(text, candidate_labels=frame_categories)
return model_result["labels"][:2] # Top 2 frame labels
# Extract hashtags
def extract_hashtags(text):
return re.findall(r"#\w+", text)
# Extract captions from DOCX file
def extract_captions_from_docx(docx_file):
doc = Document(docx_file)
captions = {}
current_post = None
for para in doc.paragraphs:
text = para.text.strip()
if re.match(r"Post \d+", text, re.IGNORECASE):
current_post = text
captions[current_post] = []
elif current_post:
captions[current_post].append(text)
return {post: " ".join(lines) for post, lines in captions.items() if lines}
# Generate a DOCX file in-memory
def generate_docx(output_data):
doc = Document()
doc.add_heading('Activism Message Analysis', 0)
for index, (caption, result) in enumerate(output_data.items(), start=1):
doc.add_heading(f"{index}. {caption}", level=1)
doc.add_paragraph("Full Caption:")
doc.add_paragraph(result['Full Caption'], style="Quote")
doc.add_paragraph(f"Language: {result['Language']}")
doc.add_paragraph(f"Tone of Caption: {', '.join(result['Tone of Caption'])}")
doc.add_paragraph(f"Number of Hashtags: {result['Hashtag Count']}")
doc.add_paragraph(f"Hashtags Found: {', '.join(result['Hashtags'])}")
doc.add_heading('Frames:', level=2)
for frame in result['Frames']:
doc.add_paragraph(frame)
doc_io = io.BytesIO()
doc.save(doc_io)
doc_io.seek(0)
return doc_io
# Streamlit app UI
st.title('AI-Powered Activism Message Analyzer')
st.write("Enter the text to analyze or upload a DOCX file containing captions:")
# Text Input
input_text = st.text_area("Input Text", height=200)
# File Upload
uploaded_file = st.file_uploader("Upload a DOCX file", type=["docx"])
# Initialize output dictionary
output_data = {}
if input_text:
language = detect_language(input_text)
tone = analyze_tone(input_text)
hashtags = extract_hashtags(input_text)
frames = extract_frames(input_text)
output_data["Manual Input"] = {
'Full Caption': input_text,
'Language': language,
'Tone of Caption': tone,
'Hashtags': hashtags,
'Hashtag Count': len(hashtags),
'Frames': frames
}
st.success("Analysis completed for text input.")
if uploaded_file:
captions = extract_captions_from_docx(uploaded_file)
for caption, text in captions.items():
language = detect_language(text)
tone = analyze_tone(text)
hashtags = extract_hashtags(text)
frames = extract_frames(text)
output_data[caption] = {
'Full Caption': text,
'Language': language,
'Tone of Caption': tone,
'Hashtags': hashtags,
'Hashtag Count': len(hashtags),
'Frames': frames
}
st.success(f"Analysis completed for {len(captions)} posts from the DOCX file.")
# Display results
if output_data:
with st.expander("Generated Output"):
st.subheader("Analysis Results")
for index, (caption, result) in enumerate(output_data.items(), start=1):
st.write(f"### {index}. {caption}")
st.write("**Full Caption:**")
st.write(f"> {result['Full Caption']}")
st.write(f"**Language**: {result['Language']}")
st.write(f"**Tone of Caption**: {', '.join(result['Tone of Caption'])}")
st.write(f"**Number of Hashtags**: {result['Hashtag Count']}")
st.write(f"**Hashtags Found:** {', '.join(result['Hashtags'])}")
st.write("**Frames**:")
for frame in result['Frames']:
st.write(f"- {frame}")
docx_file = generate_docx(output_data)
if docx_file:
st.download_button(
label="Download Analysis as DOCX",
data=docx_file,
file_name="activism_message_analysis.docx",
mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
)
|