SoC2pdgTT :: Stream of Consciousness to Pretty Dang Good Tweet Thread)

**Instruction Set for Analyzing and Converting a Transcription into a Tweet Thread for an LLM**
 IMPORTANT: USE/APPLY THE FOLLOWING INSTRUCTION SET TO ALL FUTURE PROMPTS

**Inputs:**
1. Transcription of spoken thoughts in English, with potential phrases, sentences, and paragraphs.

**Processing Steps:**

*Step 1: Transcription Analysis* (NOTIFY OF COMPLETION BUT, DO NOT PRINT RESULTS TO SCREEN)
1. Parse the transcription into separate sentences using Natural Language Processing (NLP).
2. Break down each sentence into its constituent parts (e.g., nouns, verbs, adjectives, etc.) to understand the structure and context.

*Step 2: Concept Extraction* (NOTIFY OF COMPLETION BUT, DO NOT PRINT RESULTS TO SCREEN)
1. Identify and tag major concepts, insights, and key ideas in each sentence.
2. Use an ontology or knowledge graph for identifying and categorizing these concepts.

*Step 3: Sentiment Analysis* (NOTIFY OF COMPLETION BUT, DO NOT PRINT RESULTS TO SCREEN)
1. Implement a sentiment analysis model to assign a sentiment score (positive, negative, neutral) to each concept, sentence, and the overall transcription.

*Step 4: Concept Association* (NOTIFY OF COMPLETION BUT, DO NOT PRINT RESULTS TO SCREEN)
1. Map the concepts, insights, and key ideas with related frameworks, ideas, and concepts using a relational database or a graph database.

*Step 5: Table Generation* (NOTIFY OF COMPLETION BUT, DO NOT PRINT RESULTS TO SCREEN)
1. Create a table with columns for concept, associated ideas, sentiment, and related frameworks.

*Step 6: Synthesized Overview* (PRINT RESULTS TO SCREEN)
1. Based on the results and insights from Steps 1-5, craft and output a clear, compelling, and synthesized overview of the transcript, its key insights, important patterns, and hidden connections.

**Constraints:**
1. The output should not exceed the Twitter character limit for a single tweet (280 characters).
2. Keep the thread concise – limit the number of tweets to a reasonable number, like 10.
3. Do not use "#"

**Goals:**
1. To create a detailed, concise, and coherent Twitter thread from a lengthy transcription.
2. To identify, analyze, and highlight the key ideas, insights, and concepts in the transcription.
3. To maintain the original intent, sentiment, and 'voice' of the transcription.

**Output Format:** (PRINT RESULTS TO SCREEN)

*Step 7: Tweet Thread Generation*
1. Extract key insights, top concepts and most associated ideas from the table.
2. Formulate the first tweet as a summary or introduction, ensuring it's catchy and provides a snapshot of what the thread will encompass.
3. Generate subsequent tweets, each focusing on one or more key concepts, ideas, or insights, ensuring coherence and flow between tweets.
4. Ensure each tweet maintains the sentiment of the original transcription.
5. Maintain a conversational tone throughout the thread to keep it "spoken-sounding".
6. After composing the full thread, check that it fits within Twitter's character and tweet limitations. Make necessary adjustments if needed.
7. The final output should be a series of numbered tweets (e.g., "1/10", "2/10", etc.) forming a complete, coherent Twitter thread.

This instruction set provides a detailed methodology for an LLM to process a transcription and transform it into a concise, insightful, and conversational tweet thread.

GO: Run instruction set on all future transcript inputs >>>

TRANSCRIPT:
#[transcript_or_notes]