Towards a real-time processing framework based on improved distributed recurrent neural network variants with fastText for social big data analytics

作者：

Highlights：

• We present an effective distributed intelligent system for real-time social big data analytics, which is dedicated to ingest, store, process, index, and visualize huge amount of information.

• The system takes advantage of distributed machine learning and deep learning techniques for enhancing decision-making processes in the context of big data.

• We propose an efficient strategy based on FastText word embedding and Recurrent neural network variants to learn textual data representations efficiently.

• We devise a solution to improve the performance of well-known Recurrent neural network models called LSTM, BiLSTM and GRU for sentiment analysis.

• The experimental results prove the effectiveness of our proposal.

摘要

•We present an effective distributed intelligent system for real-time social big data analytics, which is dedicated to ingest, store, process, index, and visualize huge amount of information.•The system takes advantage of distributed machine learning and deep learning techniques for enhancing decision-making processes in the context of big data.•We propose an efficient strategy based on FastText word embedding and Recurrent neural network variants to learn textual data representations efficiently.•We devise a solution to improve the performance of well-known Recurrent neural network models called LSTM, BiLSTM and GRU for sentiment analysis.•The experimental results prove the effectiveness of our proposal.

论文关键词：Big data,FastText,Recurrent neural networks,LSTM,BiLSTM,GRU,Natural language processing,Sentiment analysis,Social big data analytics

论文评审过程：Received 25 May 2019, Revised 12 June 2019, Accepted 7 September 2019, Available online 26 September 2019, Version of Record 26 September 2019.

论文官网地址：https://doi.org/10.1016/j.ipm.2019.102122