Ad Text Classification with Transformer-Based Natural Language Processing Methods

TL;DR

This paper presents a transformer-based NLP method using BERT for automatic classification of online ad texts across 12 sectors, demonstrating effective sector-wise categorization for Turkish language data.

Contribution

It introduces a BERT-based approach specifically tailored for Turkish ad text classification, expanding NLP applications in advertising sector analysis.

Findings

High classification accuracy achieved with BERT model

Effective sector-wise categorization demonstrated

Applicable to Turkish language online advertising texts

Abstract

In this study, a natural language processing-based (NLP-based) method is proposed for the sector-wise automatic classification of ad texts created on online advertising platforms. Our data set consists of approximately 21,000 labeled advertising texts from 12 different sectors. In the study, the Bidirectional Encoder Representations from Transformers (BERT) model, which is a transformer-based language model that is recently used in fields such as text classification in the natural language processing literature, was used. The classification efficiencies obtained using a pre-trained BERT model for the Turkish language are shown in detail.