Implemented NLP techniques for semantic analysis

• Day: 2023-11-19
• Time: 17:15 to 19:30
• Project: Dev
• Workspace: WP 2: Operational
• Status: In Progress
• Priority: MEDIUM
• Assignee: Matías Nehuen Iglesias
• Tags: NLP, Python, Semantic Analysis, Text Processing, Spacy

Description

Session Goal

This session focused on implementing Natural Language Processing (NLP) techniques for semantic analysis, specifically targeting the context of the word ‘docentes’.

Key Activities

• Exporting Word Counts: A Python script was used to export word count data to a CSV file using the pandas library.
• Text Processing: Replaced ellipses in text processing scripts to ensure proper word separation.
• NLP Planning: Discussed and outlined NLP techniques such as sentiment analysis, topic modeling, and named entity recognition for analyzing speeches and semantic understanding.
• Semantic Analysis Preparation: Prepared a text file ‘docentes_context.txt’ for semantic analysis and developed a Python script to extract contexts of the word ‘docentes’.
• POS Tagging Strategy: Developed a strategy using Part-of-Speech tagging to analyze contexts of ‘docentes’ using spaCy.
• Language Model Installation: Installed the Spanish language model for spaCy to facilitate NLP tasks in Spanish.

Achievements

• Successfully exported word count data to CSV format.
• Developed scripts for text and semantic analysis, focusing on the term ‘docentes’.
• Installed necessary NLP tools and models for Spanish language processing.

Pending Tasks

• Further analysis of the extracted contexts using the installed NLP models and techniques.
• Implementation of sentiment analysis and topic modeling on the ‘docentes’ contexts.
• Evaluation of the effectiveness of the NLP strategies implemented.

Evidence

• source_file=2023-11-19.sessions.jsonl, line_number=1, event_count=0, session_id=0441d3571eeeeadcb1d6e20c176394873fad7dc3bc9d4b436201693a7a2dd49a
• event_ids: []