Update tweet_analyzer.py

tweet_analyzer.py

@@ -120,14 +120,21 @@ class TweetDatasetProcessor:
         ]
 
         # Extract historical topics and add them to additional contexts
-        historical_topics = self.analyze_topics()
+        historical_topics = self.analyze_topics(n_topics=10)  # Consider more topics for greater diversity
         additional_contexts.extend(historical_topics)
 
         # Randomly select multiple contexts to increase diversity
         selected_contexts = random.sample(additional_contexts, min(3, len(additional_contexts)))
 
+        # Randomly sample tweets across different time periods to avoid repetition of topics
+        tweet_sample = random.sample(self.tweets, min(30, len(self.tweets)))  # Increase sample size for diversity
+        all_tweets = [tweet['content'] for tweet in tweet_sample]
+
+        # If personality profile is too long, truncate it (adjust length as needed)
+        personality_profile_excerpt = self.personality_profile[:1000]  # Truncate profile to first 1000 characters
+
         generation_prompt = f"""Based on this personality profile:
-        {self.personality_profile}
+        {personality_profile_excerpt}
         Current context or topic (if any):
         {context}
         Additionally, consider these contexts to increase diversity: