Sentiment analysis has been a hot research topic in natural language processing and data mining fields in the last decade. Recently, deep neural network (DNN) models are being applied to sentiment analysis tasks to obtain promising results. Among various neural architectures applied for sentiment analysis, long short-term memory (LSTM) models and its variants such as gated recurrent unit (GRU) have attracted increasing attention. Although these models are capable of processing sequences of arbitrary length, using them in the feature extraction layer of a DNN makes the feature space high dimensional. Another drawback of such models is that they consider different features equally important. To address these problems, we propose an Attention-based Bidirectional CNN-RNN Deep Model (ABCDM). By utilizing two independent bidirectional LSTM and GRU layers, ABCDM will extract both past and future contexts by considering temporal information flow in both directions. Also, the attention mechanism is applied on the outputs of bidirectional layers of ABCDM to put more or less emphasis on different words. To reduce the dimensionality of features and extract position-invariant local features, ABCDM utilizes convolution and pooling mechanisms. The effectiveness of ABCDM is evaluated on sentiment polarity detection which is the most common and essential task of sentiment analysis. Experiments were conducted on five review and three Twitter datasets. The results of comparing ABCDM with six recently proposed DNNs for sentiment analysis show that ABCDM achieves state-of-the-art results on both long review and short tweet polarity classification.

中文翻译：

---

ABCDM：一种基于注意力的双向 CNN-RNN 情感分析深度模型

情感分析是近十年来自然语言处理和数据挖掘领域的研究热点。最近，深度神经网络（DNN）模型正在应用于情感分析任务，以获得有希望的结果。在用于情感分析的各种神经架构中，长短期记忆（LSTM）模型及其变体（例如门控循环单元（GRU））引起了越来越多的关注。尽管这些模型能够处理任意长度的序列，但在 DNN 的特征提取层中使用它们会使特征空间变得高维。此类模型的另一个缺点是它们认为不同的特征同等重要。为了解决这些问题，我们提出了一种基于注意力的双向 CNN-RNN 深度模型（ABCDM）。通过利用两个独立的双向 LSTM 和 GRU 层，ABCDM 将通过考虑两个方向的时间信息流来提取过去和未来的上下文。此外，注意力机制应用于 ABCDM 双向层的输出，以或多或少地强调不同的单词。为了降低特征的维数并提取位置不变的局部特征，ABCDM 利用了卷积和池化机制。 ABCDM 的有效性是通过情感极性检测来评估的，这是情感分析中最常见和最重要的任务。在五个评论数据集和三个 Twitter 数据集上进行了实验。将 ABCDM 与最近提出的六个用于情感分析的 DNN 进行比较的结果表明，ABCDM 在长评论和短推文极性分类上都取得了最先进的结果。