Abstract
Document level Urdu Sentiment Analysis (SA) is a challenging Natural Language Processing (NLP) task as it deals with large documents in a resource-poor language. In large documents, there are ample amounts of words that exhibit different viewpoints. Deep learning (DL) models comprise of complex neural network architectures that have the ability to learn diverse features of the data to classify various sentiments. Besides audio, image and video classification; DL algorithms are now extensively used in text-based classification problems. To explore the powerful DL techniques for Urdu SA, we have applied five different DL architectures namely, Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), Bidirectional Encoder Representation from Transformer (BERT). In this paper, we have proposed a DL hybrid model that integrates BiLSTM with Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN). The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pretrained Urdu word embeddings that are suitable for (SA) at the document level. Results of these techniques are evaluated and our proposed model outperforms all other DL techniques for Urdu SA. BiLSTM-SLMFCNN outperformed the baseline DL models and achieved 83{\%}, 79{\%}, 83{\%} and 94{\%} accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.
Abstract (translated)
文档级别的乌尔都语情感分析（SA）是一项具有挑战性的自然语言处理（NLP）任务，因为它涉及在资源有限的语言中处理大量文本。在大型文档中，有许多词汇展示了不同的观点和视角。深度学习（DL）模型包含复杂的神经网络架构，能够从数据中学习各种特征以分类不同的情感。除了音频、图像和视频分类之外，如今深度学习算法也被广泛应用于基于文本的分类问题。 为了探索强大的DL技术用于乌尔都语情感分析，我们应用了五种不同的DL架构：双向长短期记忆（BiLSTM）、卷积神经网络（CNN）、带有双向长短期记忆的卷积神经网络（CNN-BiLSTM）、变压器编码器表示从变换器（BERT）。在此论文中，我们提出了一种将双向长短期记忆与单层多滤波卷积神经网络相结合的DL混合模型（BiLSTM-SLMFCNN）。我们将所提出的和基准方法应用于乌尔都语客户支持数据集和IMDb乌尔都语电影评论数据集，并使用了适用于文档级情感分析的预训练乌尔都词嵌入。我们评估了这些技术的结果，我们的提议模型在乌尔都语SA中优于所有其他DL技术。 BiLSTM-SLMFCNN超越了基准DL模型，在小型、中型和大型IMDb乌尔都语电影评论数据集以及乌尔都语客户支持数据集中分别实现了83%、79%、83%和94%的准确率。
URL
https://arxiv.org/abs/2501.17175
