Update annotated_casl_app.py

annotated_casl_app.py

@@ -182,13 +182,24 @@ def call_claude_api(prompt):
     return call_claude_api_quick_analysis(prompt)
 
 def answer_quick_question(transcript_content, question, age, gender, slp_notes):
-    """Answer a specific question about the transcript quickly"""
+    """Answer a specific question about the transcript quickly using annotated version for accuracy"""
     if not transcript_content or len(transcript_content.strip()) < 20:
         return "Error: Please provide a transcript for analysis."
     
     if not question or len(question.strip()) < 5:
         return "Error: Please provide a specific question."
     
+    # First, annotate the transcript to get accurate markers
+    logger.info("Annotating transcript for accurate question answering...")
+    annotated_transcript = annotate_transcript(transcript_content, age, gender, slp_notes)
+    
+    # Check if annotation was successful
+    if annotated_transcript.startswith("Error") or annotated_transcript.startswith("ANNOTATION INCOMPLETE"):
+        logger.warning("Using original transcript due to annotation issues")
+        analysis_transcript = transcript_content
+    else:
+        analysis_transcript = annotated_transcript
+    
     # Add SLP notes to the prompt if provided
     notes_section = ""
     if slp_notes and slp_notes.strip():
@@ -201,14 +212,24 @@ def answer_quick_question(transcript_content, question, age, gender, slp_notes):
     prompt = f"""
     You are a speech-language pathologist answering a specific question about a speech sample.
     
-    TRANSCRIPT:
-    {transcript_content}{notes_section}
+    TRANSCRIPT (with annotation markers for reference):
+    {analysis_transcript}{notes_section}
+    
+    ANNOTATION MARKER REFERENCE:
+    FLUENCY: [FILLER], [FALSE_START], [REPETITION], [REVISION], [PAUSE]
+    WORD RETRIEVAL: [CIRCUMLOCUTION], [INCOMPLETE], [GENERIC], [WORD_SEARCH]
+    GRAMMAR: [GRAM_ERROR], [SYNTAX_ERROR], [MORPH_ERROR], [RUN_ON]
+    VOCABULARY: [SIMPLE_VOCAB], [COMPLEX_VOCAB], [SEMANTIC_ERROR]
+    PRAGMATICS: [TOPIC_SHIFT], [TANGENT], [INAPPROPRIATE], [COHERENCE_BREAK]
+    SENTENCE STRUCTURE: [SIMPLE_SENT], [COMPLEX_SENT], [COMPOUND_SENT], [FIGURATIVE]
+    OTHER: [PRONOUN_REF], [MAZING], [PERSEVERATION]
     
     QUESTION: {question}
     
     INSTRUCTIONS:
     Provide a focused, detailed answer to the specific question asked
     Include specific examples from the transcript with exact quotes
+    Use the annotation markers to identify and count specific features accurately
     Provide quantitative data when relevant (counts, percentages, rates)
     Provide objective data interpretation only
     Keep the response focused on the question but thorough in analysis
@@ -221,10 +242,21 @@ def answer_quick_question(transcript_content, question, age, gender, slp_notes):
     return call_claude_api_quick_analysis(prompt)
 
 def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_notes):
-    """Perform targeted analysis of a specific area"""
+    """Perform targeted analysis of a specific area using annotated transcript for accuracy"""
     if not transcript_content or len(transcript_content.strip()) < 20:
         return "Error: Please provide a transcript for analysis."
     
+    # First, annotate the transcript to get accurate markers
+    logger.info("Annotating transcript for accurate analysis...")
+    annotated_transcript = annotate_transcript(transcript_content, age, gender, slp_notes)
+    
+    # Check if annotation was successful
+    if annotated_transcript.startswith("Error") or annotated_transcript.startswith("ANNOTATION INCOMPLETE"):
+        logger.warning("Using original transcript due to annotation issues")
+        analysis_transcript = transcript_content
+    else:
+        analysis_transcript = annotated_transcript
+    
     # Add SLP notes to the prompt if provided
     notes_section = ""
     if slp_notes and slp_notes.strip():
@@ -237,198 +269,255 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
     # Define analysis prompts for different areas
     analysis_prompts = {
         "Fluency and Disfluencies": """
-        Conduct a comprehensive FLUENCY ANALYSIS focusing on:
+        Conduct a comprehensive FLUENCY ANALYSIS using annotation markers as reference.
+        
+        TRANSCRIPT WITH ANNOTATION MARKERS:
+        {analysis_transcript}{notes_section}
+        
+        MARKER REFERENCE:
+        [FILLER] = filler words (um, uh, like, you know, etc.)
+        [FALSE_START] = false starts and self-corrections
+        [REPETITION] = word/phrase repetitions
+        [REVISION] = revisions and restarts
+        [PAUSE] = hesitations and pauses
         
         1. DISFLUENCY TYPES AND COUNTS:
-        Count and quote ALL filler words ("um", "uh", "like", "you know", etc.)
-        Count and quote ALL false starts and self-corrections
-        Count and quote ALL word/phrase repetitions
-        Count and quote ALL revisions and restarts
-        Count and quote ALL prolongations or blocks (if noted)
+        Count each marker type precisely from the annotated transcript
+        Provide exact quotes showing each marker
+        Calculate rates per 100 words
         
         2. DISFLUENCY PATTERNS:
-        Calculate disfluency rate per 100 words
-        Identify most frequent disfluency types
-        Analyze clustering patterns
+        Identify most frequent disfluency types by count
+        Analyze clustering patterns where disfluencies concentrate
         Assess impact on communication effectiveness
         
         3. FLUENCY FACILITATORS:
-        Identify fluent segments and their characteristics
-        Note any fluency-enhancing contexts
+        Identify fluent segments with no markers
+        Note contexts that show high fluency
         Assess overall speech rhythm and flow
         
         4. OBJECTIVE SUMMARY:
-        Provide data summary only
-        List observed patterns
+        Provide data summary with counts and rates
+        List observed patterns only
         
-        IMPORTANT: Do NOT use asterisks (**), hashtags (#), or bold formatting in your response. Use plain text only.
+        Do NOT use asterisks (**), hashtags (#), or bold formatting. Use plain text only.
         """,
         
         "Grammar and Syntax": """
-        Conduct a comprehensive GRAMMATICAL ANALYSIS focusing on:
+        Conduct a comprehensive GRAMMATICAL ANALYSIS using annotation markers as reference.
+        
+        TRANSCRIPT WITH ANNOTATION MARKERS:
+        {analysis_transcript}{notes_section}
+        
+        MARKER REFERENCE:
+        [GRAM_ERROR] = grammatical errors
+        [SYNTAX_ERROR] = word order/syntax problems
+        [MORPH_ERROR] = morphological errors (plurals, tense, etc.)
+        [RUN_ON] = run-on sentences
         
         1. MORPHOLOGICAL ANALYSIS:
-        Count and categorize ALL grammatical morphemes (plurals, past tense, etc.)
-        Identify missing obligatory morphemes with specific examples
-        Analyze morphological error patterns
+        Count [MORPH_ERROR] markers and categorize by type
+        Identify patterns in morphological errors
+        Analyze error frequency
         
         2. SYNTACTIC STRUCTURES:
-        Analyze sentence types (simple, compound, complex)
-        Count and quote ALL grammatical errors
-        Assess word order and sentence construction
-        Evaluate use of conjunctions and subordination
+        Analyze [SIMPLE_SENT], [COMPOUND_SENT], [COMPLEX_SENT] markers
+        Count [SYNTAX_ERROR] and [GRAM_ERROR] markers
+        Assess word order patterns
+        Evaluate conjunction and subordination use
         
         3. VERB USAGE:
-        Analyze tense consistency and accuracy
+        Identify [GRAM_ERROR] markers related to verbs
+        Analyze tense consistency
         Count subject-verb agreement errors
-        Assess auxiliary verb usage
         
         4. OBJECTIVE SUMMARY:
         List primary grammatical patterns observed
-        Provide data summary only
+        Provide count data only
         
-        IMPORTANT: Do NOT use asterisks (**), hashtags (#), or bold formatting in your response. Use plain text only.
+        Do NOT use asterisks (**), hashtags (#), or bold formatting. Use plain text only.
         """,
         
         "Vocabulary and Semantics": """
-        Conduct a comprehensive VOCABULARY ANALYSIS focusing on:
+        Conduct a comprehensive VOCABULARY ANALYSIS using annotation markers as reference.
+        
+        TRANSCRIPT WITH ANNOTATION MARKERS:
+        {analysis_transcript}{notes_section}
+        
+        MARKER REFERENCE:
+        [SIMPLE_VOCAB] = basic/high-frequency words
+        [COMPLEX_VOCAB] = sophisticated/low-frequency words
+        [SEMANTIC_ERROR] = inappropriate word choices
+        [GENERIC] = vague terms (thing, stuff)
+        [CIRCUMLOCUTION] = roundabout descriptions
+        [WORD_SEARCH] = explicit word-finding attempts
         
         1. LEXICAL DIVERSITY:
-        Calculate Type-Token Ratio (TTR)
-        Identify vocabulary sophistication levels
-        Count unique vs. repeated words
+        Count [SIMPLE_VOCAB] and [COMPLEX_VOCAB] markers
+        Calculate vocabulary sophistication ratio
+        Identify vocabulary diversity patterns
         
         2. SEMANTIC ACCURACY:
-        Identify and quote ALL semantic errors or inappropriate word choices
-        Analyze word-finding difficulties and circumlocutions
-        Assess precision of vocabulary use
+        Count [SEMANTIC_ERROR] markers with quotes
+        Identify [GENERIC] term usage
+        Count [CIRCUMLOCUTION] and [WORD_SEARCH] markers
+        Assess word precision
         
         3. VOCABULARY CATEGORIES:
-        Categorize vocabulary by semantic fields
-        Identify high-frequency vs. low-frequency words
-        Assess academic vs. conversational vocabulary
+        Analyze patterns in vocabulary type markers
+        Identify high-frequency vs. low-frequency word usage
+        Assess conversational vs. academic vocabulary
         
         4. WORD RETRIEVAL:
-        Count and analyze word-finding pauses
+        Count word-finding difficulties [WORD_SEARCH], [CIRCUMLOCUTION], [GENERIC]
         Identify compensatory strategies
-        Assess overall lexical access efficiency
+        Assess retrieval efficiency by frequency
         
         5. OBJECTIVE SUMMARY:
-        List vocabulary patterns observed
+        List vocabulary patterns observed with counts
         Provide data summary only
         
-        IMPORTANT: Do NOT use asterisks (**), hashtags (#), or bold formatting in your response. Use plain text only.
+        Do NOT use asterisks (**), hashtags (#), or bold formatting. Use plain text only.
         """,
         
         "Pragmatics and Discourse": """
-        Conduct a comprehensive PRAGMATIC ANALYSIS focusing on:
+        Conduct a comprehensive PRAGMATIC ANALYSIS using annotation markers as reference.
+        
+        TRANSCRIPT WITH ANNOTATION MARKERS:
+        {analysis_transcript}{notes_section}
+        
+        MARKER REFERENCE:
+        [TOPIC_SHIFT] = topic changes
+        [TANGENT] = tangential/off-topic speech
+        [INAPPROPRIATE] = inappropriate content
+        [COHERENCE_BREAK] = incoherent statements
+        [PRONOUN_REF] = unclear pronoun references
         
         1. DISCOURSE ORGANIZATION:
-        Analyze topic initiation, maintenance, and transitions
+        Count [TOPIC_SHIFT] and [TANGENT] markers
         Assess narrative structure and coherence
-        Evaluate logical sequencing of ideas
+        Evaluate logical idea sequencing
         
         2. CONVERSATIONAL SKILLS:
-        Assess turn-taking appropriateness
-        Analyze response relevance and appropriateness
-        Evaluate social communication effectiveness
+        Analyze topic maintenance between [TOPIC_SHIFT] markers
+        Assess response appropriateness
+        Evaluate communication effectiveness
         
         3. REFERENTIAL COMMUNICATION:
-        Count and analyze unclear pronoun references
-        Assess use of demonstratives ("this," "that")
-        Evaluate overall referential clarity
+        Count [PRONOUN_REF] markers
+        Assess clarity of pronoun use
+        Evaluate referential precision
         
         4. PRAGMATIC APPROPRIATENESS:
-        Identify any inappropriate content or responses
-        Assess contextual appropriateness
-        Evaluate social awareness in communication
+        Count [INAPPROPRIATE] markers if present
+        Assess contextual appropriateness of content
+        Evaluate social communication awareness
         
         5. OBJECTIVE SUMMARY:
-        List pragmatic patterns observed
+        List pragmatic patterns observed with marker counts
         Provide data summary only
         
-        IMPORTANT: Do NOT use asterisks (**), hashtags (#), or bold formatting in your response. Use plain text only.
+        Do NOT use asterisks (**), hashtags (#), or bold formatting. Use plain text only.
         """,
         
         "Sentence Complexity": """
-        Conduct a comprehensive SENTENCE COMPLEXITY ANALYSIS focusing on:
+        Conduct a comprehensive SENTENCE COMPLEXITY ANALYSIS using annotation markers as reference.
+        
+        TRANSCRIPT WITH ANNOTATION MARKERS:
+        {analysis_transcript}{notes_section}
+        
+        MARKER REFERENCE:
+        [SIMPLE_SENT] = simple sentences
+        [COMPOUND_SENT] = compound sentences
+        [COMPLEX_SENT] = complex sentences
+        [FIGURATIVE] = figurative language/idioms
         
         1. SENTENCE TYPES:
-        Count and categorize simple sentences with examples
-        Count and categorize compound sentences with examples
-        Count and categorize complex sentences with examples
+        Count [SIMPLE_SENT], [COMPOUND_SENT], [COMPLEX_SENT] markers
+        Calculate percentage distribution of each type
+        Provide examples of each type
         
         2. CLAUSE ANALYSIS:
-        Calculate clauses per utterance
-        Analyze subordinate clause usage
-        Assess coordination patterns
+        Analyze clause density from complex sentence markers
+        Count subordinate and coordinate clause patterns
+        Assess coordination and subordination use
         
         3. PHRASE STRUCTURES:
-        Analyze noun phrase complexity
-        Assess verb phrase elaboration
+        Analyze complexity patterns within sentence markers
+        Assess phrase elaboration levels
         Evaluate prepositional phrase usage
         
         4. SYNTACTIC MATURITY:
-        Calculate Mean Length of Utterance (MLU)
+        Calculate Mean Length of Utterance (MLU) from sentence length patterns
         List syntactic patterns observed
         
         5. OBJECTIVE SUMMARY:
-        Provide complexity data summary
+        Provide complexity data with counts and percentages
         List observed patterns only
         
-        IMPORTANT: Do NOT use asterisks (**), hashtags (#), or bold formatting in your response. Use plain text only.
+        Do NOT use asterisks (**), hashtags (#), or bold formatting. Use plain text only.
         """,
         
         "Word Finding and Retrieval": """
-        Conduct a comprehensive WORD RETRIEVAL ANALYSIS focusing on:
+        Conduct a comprehensive WORD RETRIEVAL ANALYSIS using annotation markers as reference.
+        
+        TRANSCRIPT WITH ANNOTATION MARKERS:
+        {analysis_transcript}{notes_section}
+        
+        MARKER REFERENCE:
+        [WORD_SEARCH] = explicit word-finding attempts
+        [CIRCUMLOCUTION] = roundabout descriptions as workarounds
+        [GENERIC] = vague terms (thing, stuff, whatsit)
+        [INCOMPLETE] = abandoned thoughts/word-finding failures
         
         1. WORD-FINDING DIFFICULTIES:
-        Count and quote ALL instances of word-finding pauses
-        Identify and quote ALL circumlocutions
-        Count and quote ALL use of generic terms ("thing," "stuff")
+        Count [WORD_SEARCH], [CIRCUMLOCUTION], [GENERIC], [INCOMPLETE] markers
+        Provide exact quotes showing each type
+        Calculate frequency of each difficulty type
         
         2. RETRIEVAL STRATEGIES:
-        Identify compensatory strategies used
-        Analyze self-cueing attempts
-        Assess success rate of retrieval attempts
+        Identify compensatory strategies from marker patterns
+        Analyze self-cueing attempts marked with [WORD_SEARCH]
+        Assess success rate from [CIRCUMLOCUTION] effectiveness
         
         3. ERROR PATTERNS:
-        Categorize word-finding errors by type
+        Categorize word-finding issues by marker type
         Identify semantic vs. phonological retrieval issues
         Analyze error consistency patterns
         
         4. CONTEXTUAL FACTORS:
-        Identify contexts that facilitate vs. hinder retrieval
-        Assess impact of topic familiarity
-        Evaluate effect of linguistic complexity on retrieval
+        Identify contexts that show high [WORD_SEARCH] density
+        Assess topic complexity impact on word retrieval
+        Evaluate linguistic complexity effects
         
         5. OBJECTIVE SUMMARY:
-        List word-finding patterns observed
+        List word-finding patterns observed with marker counts
         Provide data summary only
         
-        IMPORTANT: Do NOT use asterisks (**), hashtags (#), or bold formatting in your response. Use plain text only.
+        Do NOT use asterisks (**), hashtags (#), or bold formatting. Use plain text only.
         """
     }
     
     if analysis_area not in analysis_prompts:
         return f"Error: Analysis area '{analysis_area}' not recognized. Available areas: {', '.join(analysis_prompts.keys())}"
     
+    # Get the base prompt and insert the analysis transcript
+    base_prompt_template = analysis_prompts[analysis_area]
+    base_prompt = base_prompt_template.format(analysis_transcript=analysis_transcript, notes_section=notes_section)
+    
     prompt = f"""
     You are a speech-language pathologist conducting a targeted analysis of a specific area.
     
-    TRANSCRIPT:
-    {transcript_content}{notes_section}
-    
     ANALYSIS FOCUS: {analysis_area}
     
-    {analysis_prompts[analysis_area]}
+    {base_prompt}
     
     INSTRUCTIONS:
-    - Provide specific examples with exact quotes from the transcript
-    - Include quantitative data (counts, percentages, rates per 100 words)
-    - Provide objective data interpretation only
-    - Focus on measurable observations
-    - Be thorough but focused on the specified area
+    Provide specific examples with exact quotes from the transcript
+    Include quantitative data using marker counts and percentages
+    Provide objective data interpretation only
+    Focus on measurable observations
+    Be thorough but focused on the specified area
     
     Conduct the targeted analysis:
     """