Sentiment analysis with deep neural networks: comparative study and performance assessment
- PDF / 2,655,023 Bytes
- 41 Pages / 439.37 x 666.142 pts Page_size
- 78 Downloads / 177 Views
Sentiment analysis with deep neural networks: comparative study and performance assessment Ramesh Wadawadagi1 · Veerappa Pagi1
© Springer Nature B.V. 2020
Abstract The current decade has witnessed the remarkable developments in the field of artificial intelligence, and the revolution of deep learning has transformed the whole artificial intelligence industry. Eventually, deep learning techniques have become essential components of any model in today’s computational world. Nevertheless, deep learning techniques promise a high degree of automation with generalized rule extraction for both text and sentiment classification tasks. This article aims to provide an empirical study on various deep neural networks (DNN) used for sentiment classification and its applications. In the preliminary step, the research carries out a study on several contemporary DNN models and their underlying theories. Furthermore, the performances of different DNN models discussed in the literature are estimated through the experiments conducted over sentiment datasets. Following this study, the effect of fine-tuning various hyperparameters on each model’s performance is also examined. Towards a better comprehension of the empirical results, few simple techniques from data visualization have been employed. This empirical study ensures deep learning practitioners with insights into ways to adapt stable DNN techniques for many sentiment analysis tasks. Keywords Deep neural networks · Sentiment analysis · Performance evaluation · Aspectbased sentiment analysis · Opinion mining
1 Introduction The explosive growth of opinion content generated through commercial websites and recent advances in data analytics together have placed new challenges and opportunities (Khan et al. 2017; Chaturvedi et al. 2018; Wadawadagi and Pagi 2019a). Investigating peculiar and potentially useful patterns from a large collection of user-generated content (UGC) is crucial for many sentiment analysis tasks (Medhat et al. 2013; Chen and Lee 2019). Sentiment analysis techniques are specially used to recognize and extract subjective content in source data to assist an enterprise in understanding the social sentiment of their brand, product, or services (Pandarachalil et al. 2015; Krishnakumari et al. 2019). * Ramesh Wadawadagi [email protected] 1
Basaveshwar Engineering College, Bagalkot 587 102, India
13
Vol.:(0123456789)
R. Wadawadagi, V. Pagi
However, identification of sentiments in UGC faces numerous challenges, as they are composed of incomplete, noisy, and unstructured sentences, unusual expressions, ungrammatical phrases, and non-lexical terms (Hassan 2019; Wadawadagi and Pagi 2019a). Besides, it is hard to explore the correlation among opinion sentences due to the diversity of linguistic issues and makes the process of sentiment analysis still more challenging (Medhat et al. 2013; Zhang et al. 2017). Hence, to address these challenges, real-time sentiment analysis systems need to be developed for processing large volumetric opinion data in a rea
Data Loading...
