A Deep Learning Approach for Accurate Spam Detection in Text

Author First name, Last name, Institution

• Sumeera BiBi, Gomal University
• Asad Khattak, Zayed University, Abu Dhabi CampusFollow
• Hayat Ullah, Zayed University, Abu Dhabi Campus
• Muhammad Usama Asghar, Gomal University
• Muhammad Zubair Asghar, Gomal University
• Wasim Abbas, Techsacare PTE. Ltd.

Document Type

Conference Proceeding

Source of Publication

Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering Lnicst

Publication Date

4-1-2026

Abstract

In modern communication networks, spam detection remains a critical challenge due to the evolving nature of unsolicited content. This study presents a deep learning approach using a Bidirectional Long Short-Term Memory (Bi-LSTM) model for enhanced spam classification. The model is trained and evaluated on a benchmark dataset comprising 5,574 labeled SMS messages, including both spam and ham texts. Leveraging Bi-LSTM's ability to capture sequential dependencies, the proposed model achieves superior performance with an accuracy of 98%, precision of 98%, recall of 1.00, and F1-score of 0.99. These results demonstrate the effectiveness of the approach in improving spam detection accuracy over traditional methods.

DOI Link

10.1007/978-3-032-16638-8_5

ISBN

[9783032166371]

ISSN

1867-8211

Publisher

Springer Nature Switzerland

Volume

677 LNICST

First Page

50

Last Page

64

Disciplines

Computer Sciences

Keywords

Adaptive spam detection, Bi-LSTM model, Deep learning, Performance metrics, Spam detection

Scopus ID

105041056350

Recommended Citation

BiBi, Sumeera; Khattak, Asad; Ullah, Hayat; Asghar, Muhammad Usama; Asghar, Muhammad Zubair; and Abbas, Wasim, "A Deep Learning Approach for Accurate Spam Detection in Text" (2026). All Works. 8016.
https://zuscholars.zu.ac.ae/works/8016

Indexed in Scopus

yes

Open Access

no