Building a Twitter Sentiment Analysis System with Recurrent Neural Networks

This paper presents a sentiment analysis solution on tweets using Recurrent Neural Networks (RNNs). The method is can classifying tweets with an 80.74% accuracy rate, considering a binary task, after experimenting with 20 different design approaches. The solution integrates an attention mechanism ai...

Full description

Bibliographic Details
Main Authors: Sergiu Cosmin Nistor, Mircea Moca, Darie Moldovan, Delia Beatrice Oprean, Răzvan Liviu Nistor
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/21/7/2266
_version_ 1797540226852192256
author Sergiu Cosmin Nistor
Mircea Moca
Darie Moldovan
Delia Beatrice Oprean
Răzvan Liviu Nistor
author_facet Sergiu Cosmin Nistor
Mircea Moca
Darie Moldovan
Delia Beatrice Oprean
Răzvan Liviu Nistor
author_sort Sergiu Cosmin Nistor
collection DOAJ
description This paper presents a sentiment analysis solution on tweets using Recurrent Neural Networks (RNNs). The method is can classifying tweets with an 80.74% accuracy rate, considering a binary task, after experimenting with 20 different design approaches. The solution integrates an attention mechanism aiming to enhance the network, with a two-way localization system: at memory cell level and at network level. We present an in-depth literature review for Twitter sentiment analysis and the building blocks that grounded the design decisions of our solution, employed as a core classification component within a sentiment indicator of the SynergyCrowds platform.
first_indexed 2024-03-10T12:57:07Z
format Article
id doaj.art-76454d61109445ee8da2776b515af376
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-10T12:57:07Z
publishDate 2021-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-76454d61109445ee8da2776b515af3762023-11-21T11:47:09ZengMDPI AGSensors1424-82202021-03-01217226610.3390/s21072266Building a Twitter Sentiment Analysis System with Recurrent Neural NetworksSergiu Cosmin Nistor0Mircea Moca1Darie Moldovan2Delia Beatrice Oprean3Răzvan Liviu Nistor4Synergy Crowds OÜ, 10141 Tallin, EstoniaSynergy Crowds OÜ, 10141 Tallin, EstoniaBusiness Information Systems Department, Interdisciplinary Centre for Data Science, Babeş-Bolyai University, 400083 Cluj-Napoca, RomaniaCoaching Consult, 400191 Cluj-Napoca, RomaniaDepartment of Management, Babeş-Bolyai University, 400591 Cluj-Napoca, RomaniaThis paper presents a sentiment analysis solution on tweets using Recurrent Neural Networks (RNNs). The method is can classifying tweets with an 80.74% accuracy rate, considering a binary task, after experimenting with 20 different design approaches. The solution integrates an attention mechanism aiming to enhance the network, with a two-way localization system: at memory cell level and at network level. We present an in-depth literature review for Twitter sentiment analysis and the building blocks that grounded the design decisions of our solution, employed as a core classification component within a sentiment indicator of the SynergyCrowds platform.https://www.mdpi.com/1424-8220/21/7/2266sentiment analysisrecurrent neural networktwitterclassificationattention mechanism
spellingShingle Sergiu Cosmin Nistor
Mircea Moca
Darie Moldovan
Delia Beatrice Oprean
Răzvan Liviu Nistor
Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
Sensors
sentiment analysis
recurrent neural network
twitter
classification
attention mechanism
title Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
title_full Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
title_fullStr Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
title_full_unstemmed Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
title_short Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
title_sort building a twitter sentiment analysis system with recurrent neural networks
topic sentiment analysis
recurrent neural network
twitter
classification
attention mechanism
url https://www.mdpi.com/1424-8220/21/7/2266
work_keys_str_mv AT sergiucosminnistor buildingatwittersentimentanalysissystemwithrecurrentneuralnetworks
AT mirceamoca buildingatwittersentimentanalysissystemwithrecurrentneuralnetworks
AT dariemoldovan buildingatwittersentimentanalysissystemwithrecurrentneuralnetworks
AT deliabeatriceoprean buildingatwittersentimentanalysissystemwithrecurrentneuralnetworks
AT razvanliviunistor buildingatwittersentimentanalysissystemwithrecurrentneuralnetworks