Deep Learning is considered to leverage smart cities through social media sentiment analysis. The digital content in social media can be used for many smart city applications (SCAs)¹ . Classical convolutional neural networks (CNNs) are challenging to parallelize and insufficient to capture long term contextual semantic features for sentiment analysis. In this perspective, this paper initially proposes a domain-specific distributed word representation (DS-DWR)² with a considerably small corpus size induced from textual resources in social media. In DS-DWR, different Distributed Word Representations are concatenated to builds rich representations over the input sequence, which is worthwhile for infrequent and unseen terms. Second, a dilated convolutional neural network (D-CNN)³ , which is composed of three parallel dilated convolutional neural network (PD-CNN)⁴ layers and a global average pooling (GAP)⁵ layer. Our considered parallel dilated convolution reduces dimension and incorporates an extension in the size of receptive fields without the loss of local information. Further, the long-term contextual semantic information is achieved by the use of different dilation rates. Experiments demonstrate that our architecture accomplishes comparable results with multiple hyperparameters tuning for better parallelism which leads to the minimized computational cost.

深度学习被认为可以通过社交媒体情绪分析来利用智慧城市。社交媒体中的数字内容可用于许多智能城市应用程序（SCA）¹。经典卷积神经网络（CNN）难以并行化，并且不足以捕获用于情感分析的长期上下文语义特征。从这个角度来看，本文最初提出了一种特定于域的分布式单词表示（DS-DWR）²，它具有从社交媒体的文本资源中引出的相当小的语料库大小。在DS-DWR中，将不同的分布式单词表示形式连接起来，以在输入序列上构建丰富的表示形式，这对于不经常使用且看不见的术语是值得的。第二，膨胀卷积神经网络（D-CNN）^图3由三个并行的扩张卷积神经网络（PD-CNN）⁴层和全局平均池（GAP）⁵层组成。我们考虑的并行扩张卷积可减小尺寸，并在不损失本地信息的情况下合并了接收域的大小。此外，通过使用不同的膨胀率来获得长期上下文语义信息。实验表明，我们的体系结构通过多个超参数调整达到了可比的结果，从而实现了更好的并行性，从而使计算成本降至最低。