import os import pandas as pd import streamlit as st import re import logging import nltk from docx import Document import io from langdetect import detect from collections import Counter from dotenv import load_dotenv from langchain_groq import ChatGroq from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import ChatPromptTemplate from transformers import pipeline # Load environment variables load_dotenv() # Check if Groq API key is available GROQ_API_KEY = os.getenv("GROQ_API_KEY") if not GROQ_API_KEY: logging.error("Missing Groq API key. Please set the GROQ_API_KEY environment variable.") st.error("API key is missing. Please provide a valid API key.") # Initialize logging logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s") # Initialize LLM (Groq API) llm = ChatGroq(temperature=0.5, groq_api_key=GROQ_API_KEY, model_name="llama3-8b-8192") # Download required NLTK resources nltk.download("punkt") # Tone categories for fallback method tone_categories = { "Emotional": ["urgent", "violence", "disappearances", "forced", "killing", "crisis", "concern"], "Harsh": ["corrupt", "oppression", "failure", "repression", "exploit", "unjust", "authoritarian"], "Somber": ["tragedy", "loss", "pain", "sorrow", "mourning", "grief", "devastation"], "Motivational": ["rise", "resist", "mobilize", "inspire", "courage", "change", "determination"], "Informative": ["announcement", "event", "scheduled", "update", "details", "protest", "statement"], "Positive": ["progress", "unity", "hope", "victory", "together", "solidarity", "uplifting"], "Angry": ["rage", "injustice", "fury", "resentment", "outrage", "betrayal"], "Fearful": ["threat", "danger", "terror", "panic", "risk", "warning"], "Sarcastic": ["brilliant", "great job", "amazing", "what a surprise", "well done", "as expected"], "Hopeful": ["optimism", "better future", "faith", "confidence", "looking forward"] } # Frame categories for fallback method # AI-Expanded Frame Categories for More Precise Categorization # Expanded Frame Categories for Better Categorization frame_categories = { "Human Rights & Justice": { "Legal Rights & Reforms": ["law", "justice", "legal", "reforms", "legislation"], "Humanitarian Issues": ["humanitarian", "aid", "refugees", "asylum", "crisis response"], "Civil Liberties": ["freedom", "expression", "privacy", "rights violations"] }, "Political & State Accountability": { "Corruption & Governance": ["corruption", "government", "policy", "accountability", "transparency"], "Political Oppression": ["authoritarianism", "censorship", "state control", "dissent", "crackdown"], "Elections & Political Representation": ["voting", "elections", "political participation", "democracy"] }, "Gender & Patriarchy": { "Gender-Based Violence": ["violence", "domestic abuse", "sexual harassment", "femicide"], "Women's Rights & Equality": ["gender equality", "feminism", "reproductive rights", "patriarchy"], "LGBTQ+ Rights": ["queer rights", "LGBTQ+", "gender identity", "trans rights", "homophobia"] }, "Religious Freedom & Persecution": { "Religious Discrimination": ["persecution", "intolerance", "sectarianism", "faith-based violence"], "Religious Minorities' Rights": ["minorities", "blasphemy laws", "religious freedom", "forced conversion"] }, "Grassroots Mobilization": { "Community Activism": ["activism", "grassroots", "volunteering", "local organizing"], "Protests & Demonstrations": ["march", "strike", "rally", "sit-in", "boycott"], "Coalition Building": ["solidarity", "collaboration", "alliances", "mutual aid"] }, "Environmental Crisis & Activism": { "Climate Change Awareness": ["climate crisis", "global warming", "carbon emissions", "fossil fuels"], "Conservation & Sustainability": ["deforestation", "wildlife protection", "biodiversity"], "Environmental Justice": ["pollution", "water crisis", "land rights", "indigenous rights"] }, "Anti-Extremism & Anti-Violence": { "Hate Speech & Radicalization": ["hate speech", "extremism", "online radicalization", "propaganda"], "Mob & Sectarian Violence": ["mob attack", "lynching", "sectarian violence", "hate crimes"], "Counterterrorism & De-Radicalization": ["terrorism", "prevention", "peacebuilding", "rehabilitation"] }, "Social Inequality & Economic Disparities": { "Class Privilege & Labor Rights": ["classism", "labor rights", "unions", "wage gap"], "Poverty & Economic Justice": ["poverty", "inequality", "economic disparity", "wealth gap"], "Housing & Healthcare": ["housing crisis", "healthcare access", "social safety nets"] }, "Activism & Advocacy": { "Policy Advocacy & Legal Reforms": ["campaign", "policy change", "legal advocacy"], "Social Media Activism": ["hashtags", "digital activism", "awareness campaign"], "Freedom of Expression & Press": ["press freedom", "censorship", "media rights"] }, "Systemic Oppression": { "Marginalized Communities": ["minorities", "exclusion", "systemic discrimination"], "Racial & Ethnic Discrimination": ["racism", "xenophobia", "ethnic cleansing", "casteism"], "Institutional Bias": ["institutional racism", "structural oppression", "biased laws"] }, "Intersectionality": { "Multiple Oppressions": ["overlapping struggles", "intersecting identities", "double discrimination"], "Women & Marginalized Identities": ["feminism", "queer feminism", "minority women"], "Global Solidarity Movements": ["transnational activism", "cross-movement solidarity"] }, "Call to Action": { "Petitions & Direct Action": ["sign petition", "protest", "boycott"], "Fundraising & Support": ["donate", "crowdfunding", "aid support"], "Policy & Legislative Action": ["policy change", "demand action", "write to lawmakers"] }, "Empowerment & Resistance": { "Grassroots Organizing": ["community empowerment", "leadership training"], "Revolutionary Movements": ["resistance", "revolt", "revolutionary change"], "Inspiration & Motivational Messaging": ["hope", "courage", "overcoming struggles"] }, "Climate Justice": { "Indigenous Environmental Activism": ["land rights", "indigenous climate leadership"], "Corporate Accountability": ["big oil", "corporate greed", "environmental negligence"], "Sustainable Development": ["eco-friendly", "renewable energy", "circular economy"] }, "Human Rights Advocacy": { "Criminal Justice Reform": ["police brutality", "wrongful convictions", "prison reform"], "Workplace Discrimination & Labor Rights": ["workplace bias", "equal pay", "unions"], "International Human Rights": ["humanitarian law", "UN declarations", "international treaties"] } } # Detect language def detect_language(text): try: return detect(text) except Exception as e: logging.error(f"Error detecting language: {e}") return "unknown" # Extract tone using Groq API (or fallback method) def extract_tone(text): try: response = llm.chat([{"role": "system", "content": "Analyze the tone of the following text and provide descriptive tone labels."}, {"role": "user", "content": text}]) return response["choices"][0]["message"]["content"].split(", ") except Exception as e: logging.error(f"Groq API error: {e}") return extract_tone_fallback(text) # Fallback method for tone extraction def extract_tone_fallback(text): detected_tones = set() text_lower = text.lower() for category, keywords in tone_categories.items(): if any(word in text_lower for word in keywords): detected_tones.add(category) return list(detected_tones) if detected_tones else ["Neutral"] # Extract hashtags def extract_hashtags(text): return re.findall(r"#\w+", text) # Categorize frames into Major, Significant, and Minor based on frequency def categorize_frames(frame_list): frame_counter = Counter(frame_list) categorized_frames = {"Major Focus": [], "Significant Focus": [], "Minor Mention": []} sorted_frames = sorted(frame_counter.items(), key=lambda x: x[1], reverse=True) for i, (frame, count) in enumerate(sorted_frames): if i == 0: # Highest frequency frame categorized_frames["Major Focus"].append(frame) elif i < 3: # Top 3 most mentioned frames categorized_frames["Significant Focus"].append(frame) else: categorized_frames["Minor Mention"].append(frame) return categorized_frames # Extract frames using keyword matching and categorize def extract_frames_fallback(text): detected_frames = [] text_lower = text.lower() # Iterate through the activism topics to match keywords for main_category, subcategories in frame_categories.items(): for subcategory, keywords in subcategories.items(): # Check how many keywords from the subcategory are present in the text keyword_count = sum(1 for word in keywords if word in text_lower) if keyword_count > 0: # Append a tuple with main category and subcategory detected_frames.append((main_category, subcategory)) # Categorize detected frames based on their frequency return categorize_frames(detected_frames) # Extract captions from DOCX 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} # Extract metadata from Excel file def extract_metadata_from_excel(excel_file): try: df = pd.read_excel(excel_file) extracted_data = df.to_dict(orient="records") return extracted_data except Exception as e: logging.error(f"Error processing Excel file: {e}") return [] # Merge metadata with generated analysis def merge_metadata_with_generated_data(generated_data, excel_metadata): for post_data in excel_metadata: post_number = f"Post {post_data.get('Post Number', len(generated_data) + 1)}" if post_number in generated_data: generated_data[post_number].update(post_data) else: generated_data[post_number] = post_data return generated_data # Create DOCX file matching the uploaded format def create_docx_from_data(extracted_data): doc = Document() for post_number, data in extracted_data.items(): doc.add_heading(post_number, level=1) ordered_keys = [ "Post Number", "Date of Post", "Media Type", "Number of Pictures", "Number of Videos", "Number of Audios", "Likes", "Comments", "Tagged Audience", "Full Caption", "Language", "Tone", "Hashtags", "Frames" ] for key in ordered_keys: value = data.get(key, "N/A") if key in ["Tone", "Hashtags"]: value = ", ".join(value) if isinstance(value, list) else value elif key == "Frames" and isinstance(value, dict): frame_text = "\n".join([f" {category}: {', '.join([' → '.join(frame) for frame in frames])}" for category, frames in value.items() if frames]) value = f"\n{frame_text}" if frame_text else "N/A" doc.add_paragraph(f"**{key}:** {value}") doc.add_paragraph("\n") return doc # Streamlit app st.title("AI-Powered Activism Message Analyzer") st.write("Enter text or upload a DOCX/Excel file for analysis:") input_text = st.text_area("Input Text", height=200) uploaded_docx = st.file_uploader("Upload a DOCX file", type=["docx"]) uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"]) output_data = {} if input_text: output_data["Manual Input"] = { "Full Caption": input_text, "Language": detect_language(input_text), "Tone": extract_tone(input_text), "Hashtags": extract_hashtags(input_text), "Frames": extract_frames_fallback(input_text), } if uploaded_docx: captions = extract_captions_from_docx(uploaded_docx) for caption, text in captions.items(): output_data[caption] = { "Full Caption": text, "Language": detect_language(text), "Tone": extract_tone(text), "Hashtags": extract_hashtags(text), "Frames": extract_frames_fallback(text), } if uploaded_excel: excel_metadata = extract_metadata_from_excel(uploaded_excel) output_data = merge_metadata_with_generated_data(output_data, excel_metadata) # Display results in collapsible sections for better UI if output_data: for post_number, data in output_data.items(): with st.expander(post_number): for key, value in data.items(): st.write(f"**{key}:** {value}") if output_data: docx_output = create_docx_from_data(output_data) docx_io = io.BytesIO() docx_output.save(docx_io) docx_io.seek(0) st.download_button("Download Merged Analysis as DOCX", data=docx_io, file_name="merged_analysis.docx")