Work

Multi-view text classification through integrated RNN autoencoder learning of word, sentence, emotion and paragraph representations

Year: 2025

Type: article

Abstract: Text classification performance can be constrained by single-view approaches that process documents through a single representational lens and struggle to capture the multi-dimensional nature of textual information. We propose FMV-RNN-AE (Feature integration Multi-View RNN Autoencoder), an end-to-end framework that systematically integrates four complementary textual views-word-level embeddings, sentence-level representations, emotion-based features, and paragraph-level semantics. FMV-RNN-AE employs standard RNN autoencoders to learn compressed view-specific representations, followed by a learnable fusion module and joint optimization for classification, focusing on the principled integration of these components rather than introducing a fundamentally new architecture. Comprehensive evaluation across seven benchmark datasets shows consistent improvements of 4.7% compared to strong single-view approaches and 2.2-4.0% over existing multi-view methods, with particularly strong performance on sentiment-oriented tasks (93.5% accuracy on Hate Speech, 92.7% on IMDb). Compared with BERT, FMV-RNN-AE achieves comparable average accuracy while using 7.2× fewer parameters and 50% less memory, at the cost of approximately 4× higher inference latency due to sequential multi-view processing. Thus, the framework is best interpreted as a memory-efficient, task-sensitive alternative suited to latency-tolerant, batch or offline scenarios rather than real-time applications. These results highlight the potential of carefully designed multi-view autoencoder integration for improving text classification robustness across diverse domains under constrained memory budgets.

Source: Scientific Reports

DOI: 10.1038/s41598-025-31954-7

Authors: Yitao Ding, Mohamed Shalaby, Narinderjit Singh Sawaran Singh, Raed H. C. Alfilh

Institutions: Xijing University, Imam Mohammad ibn Saud Islamic University, INTI International University, Islamic University of Najaf

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,690

Funder: Al-Imam Muhammad Ibn Saud Islamic University