Adamu Lawan

Adamu Lawan

Auto-generated profile, based on publicly available information

Adamu Lawan

Beihang University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2026 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
ALAdamu Lawan
Adamu Lawan
JPJuhua Pu
Juhua Pu
YHYunusa Haruna
Yunusa Haruna
AUAliyu Umar
Aliyu Umar
MLMuhammad Lawan
Muhammad Lawan
MBMahmoud Basi
Mahmoud Basi
Multimodal Aspect-Based Sentiment Analysis (MABSA) enhances sentiment detection by integrating text with complementary modalities, such as images, for a more comprehensive understanding of aspect-level sentiment. Despite notable progress, existing MABSA methods still lack strong aspect awareness, particularly in sentences with multiple aspects and conflicting sentiments or when visual cues are misaligned with the text. Together, these issues hinder accurate modeling of aspect-focused and cross-modal dependencies, limiting the effectiveness of MABSA. To address these challenges, we propose DualKanbaFormer, a novel framework with parallel Textual and Visual KanbaFormer modules tailored for MABSA. At its core, the model introduces Aspect-Driven Sparse Attention (ADSA) with an aspect-aware attention gating mechanism, which dynamically regulates the contributions of Scope, Focus, and Proximity attention branches conditioned on the target aspect. This ensures precise alignment between aspects and opinion signals. In addition, the selective state space model Mamba strengthens aspect–opinion alignment by modeling long-range dependencies across modalities. To enhance representational expressiveness and training stability, Kolmogorov–Arnold Networks (KANs) and Dynamic Tanh (DyT) replace conventional feed-forward and normalization layers. Finally, a CNN-based multimodal gated fusion module adaptively regulates cross-modal interactions, ensuring robust alignment between textual and visual features. Experiments on two benchmark datasets demonstrate that DualKanbaFormer outperforms several state-of-the-art models.

4 November 2026
Verified
Book Chapter
Closed access
AUAliyu Umar
Aliyu Umar
SFSuleiman Farouk
Suleiman Farouk
ALAdamu Lawan
Adamu Lawan
MDMukhtar Dahiru
Mukhtar Dahiru
AAAbdullahi Abdulkadir
Abdullahi Abdulkadir
MLMaaruf Lawan
Maaruf Lawan

18 June 2025 in International Journal of Information and Communication Sciences
Verified
Journal Article
Open access
PDF file
SFSuleiman Farouk
Suleiman Farouk
AUAliyu Umar
Aliyu Umar
FSFaki Ageebee Silas
Faki Ageebee Silas
UBUsman Fodiyo Bala
Usman Fodiyo Bala
ALAdamu Lawan
Adamu Lawan
AAAbdullahi Abdulkadir
Abdullahi Abdulkadir
The dark web, an obscured and encrypted segment of the internet, serves as a nexus for illicit activities and underground communities, presenting substantial challenges for law enforcement and cybersecurity professionals. This paper explains the linguistic patterns and communication dynamics within the dark web by using the Random Forest classifier model. The Random Forest Classifier, selected for its proficiency in managing high-dimensional and noisy data, is utilized to classify and decode the cryptic language prevalent on the dark web. The model demonstrates a high accuracy of 98%, complemented by strong precision, recall, and F1-score metrics. These findings underscore the model's efficacy in identifying significant linguistic patterns and offer valuable insights into the communication mechanisms within dark web communities. Despite the promising results, this study acknowledges data quality and generalizability limitations, proposing avenues for future research to enhance model robustness and address ethical considerations in dark web analytics. This work contributes to the ongoing efforts to understand and mitigate illicit activities on the dark web through the application of machine learning and linguistic analysis.