ABSA (Aspect-Based Sentiment Analysis)

Overview

ABSA (Aspect-Based Sentiment Analysis) extracts specific topics/aspects mentioned in employee reviews and their associated sentiment. This enables the "Topics" page in the dashboard to show what employees are talking about (salary, management, work-life balance, etc.) and whether sentiment is positive, neutral, or negative for each topic.

Architecture

graph LR
    R[Reviews Table] --> A[ABSA Analyzer]
    A --> O[review_aspects Table]

    subgraph Extraction Methods
    A1[Rule-based]
    A2[AI-powered Gemini]
    end

    A -.-> A1
    A -.-> A2

Database Schema

Table: review_aspects

Column	Type	Description
id	INTEGER	Primary key
review_id	VARCHAR	FK to reviews.review_id
aspect	VARCHAR	Topic category (e.g., "salary and benefits")
sentiment	VARCHAR	positive, neutral, or negative
confidence	FLOAT	0.0-1.0 confidence score
snippet	TEXT	Optional text snippet

Predefined Aspect Categories

1. salary and benefits
2. work-life balance
3. management
4. company culture
5. career growth
6. job security
7. work environment
8. colleagues
9. training and development
10. communication

Automations & API

ABSA runs automatically after scraping via scraping_service.py.

API Endpoints

• GET /api/aspects?company=Name: Returns aspect sentiment distribution.

CLI Usage

# Analyze specific company
python backend/absa_analyzer.py --company "Audi" --limit 200

# Use rule-based only (no AI costs)
python backend/absa_analyzer.py --company "Audi" --no-ai