An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool

Luigi Lomasto; Rosario Di Florio; Andrea Ciapetti; Giuseppe Miscione; Giulia Ruggiero; Daniele Toti

cs.AIMar 12, 2026

An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool

Authors: Luigi Lomasto, Rosario Di Florio, Andrea Ciapetti, Giuseppe Miscione, Giulia Ruggiero, Daniele Toti

Organizations: Eustema S.p.A. · Allianz SE · Innovation Engineering S.r.l., Rome, Italy · Department of Sciences, Roma Tre University, Rome, Italy

Abstract

This work describes an automatic text classification method implemented in a software tool called NETHIC, which takes advantage of the inner capabilities of highly-scalable neural networks combined with the expressiveness of hierarchical taxonomies. As such, NETHIC succeeds in bringing about a mechanism for text classification that proves to be significantly effective as well as efficient. The tool had undergone an experimentation process against both a generic and a domain-specific corpus, outputting promising results. On the basis of this experimentation, NETHIC has been now further refined and extended by adding a document embedding mechanism, which has shown improvements in terms of performance on the individual networks and on the whole hierarchical model.

Figures & tables

Figure 1: General-purpose hierarchical taxonomy (upper part).

Figure 2: General-purpose hierarchical taxonomy (lower part).

Figure 4: Single ANN’s scores with BOW Dataset

Figure 5: Single ANN’s scores with Doc2Vec Dataset

Figure 6: Single ANN’s scores with BOW+Doc2Vec Dataset

Figure 7: Classification accuracy of the initial (leftmost chart) and the extended method (rightmost chart).

Figure 8: NETHIC’s original results (with only the BOW-based embedding mechanism).

Figure 9: NETHIC’s results with the introduction of the combined BOW+Doc2Vec embedding mechanism.

Text Classification

Text classification assigns text to categories such as topic, sentiment, intent, stance, or risk, supporting search, moderation, and decisions.

See all 226 papers

TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale
Aug 31, 2026Sandeep Sricharan Mukku, Albert Aristotle Nanda, Rohit PyatiTopic Modeling Semantic Mapping
Amazon
MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees
Aug 21, 2026John Cadigan, Dayne Freitag, Eric YehExplainable Text Classification Text Classification
SRI International
ModTGCN: Modularity-aware Graph Neural Networks for Text Classification
Apr 29, 2026Rajarshi Misra, Aditya Sharma, Vinti Agarwal +1Graph Neural Networks Text Classification
BITS Pilani, India · Independent Researcher

Aug 31, 2026J/K move · Enter open · S save

TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale

Sandeep Sricharan Mukku, Albert Aristotle Nanda, Rohit Pyati

Amazon

Topic Modeling Semantic Mapping Automated Evaluation Taxonomy Induction

Open paper AskPDF arXiv

Organizing unstructured feedback text into hierarchical taxonomy is a fundamental challenge in NLP, particularly in domains where feedback arrives at massive scale in varied forms such as reviews, transcripts, and surveys. Existing approaches either produce shallow hierarchies, neglect long-tail topics, or lack rigorous evaluation frameworks. We present TaxCE, a fully automated framework that constructs multi-level hierarchical taxonomies from raw text through progressive condensation of corpus content into actionable segments, deduplicated semantic units, and granular topics with definitions, which are then organized bottom-up into a hierarchy with corpus-groundedness. We also introduce three corpus-grounded evaluation metrics, Exclusivity, Exhaustivity, and Granularity (EEG), and integrate them into a metrics-in-the-loop iterative refinement mechanism that diagnoses deficiencies and applies targeted corrections until convergence. Extensive experiments demonstrate that TaxCE consistently outperforms existing baselines spanning classical topic models, neural methods, and LLM-based approaches, with average improvements of 11.8, 20.5, and 15.7 percentage points in exclusivity, exhaustivity, and granularity respectively over the strongest baseline. Human evaluation further confirms superior taxonomy quality, actionability, and navigability.

Abstract

Text Classification

Explore similar work

TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale

MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees

ModTGCN: Modularity-aware Graph Neural Networks for Text Classification