Opinion Mining From Social Media Short Texts: Does Collective Intelligence Beat Deep Learning?

@article{Tsapatsoulis2019OpinionMF,
  title={Opinion Mining From Social Media Short Texts: Does Collective Intelligence Beat Deep Learning?},
  author={Nicolas Tsapatsoulis and Constantinos Djouvas},
  journal={Frontiers in Robotics and AI},
  year={2019},
  volume={5}
}
The era of big data has, among others, three characteristics: the huge amounts of data created every day and in every form by everyday people, artificial intelligence tools to mine information from those data and effective algorithms that allow this data mining in real or close to real time. On the other hand, opinion mining in social media is nowadays an important parameter of social media marketing. Digital media giants such as Google and Facebook developed and employed their own tools for… 
Deep Learning for Opinion Mining: A Systematic Survey
TLDR
This study focuses on the literature done in the years 2015–2019 and will help the researchers and scholars to analyze the recent works in the field of Opinion mining.
Sentiment Analysis of Social Survey Data for Local City Councils
TLDR
This research was focused on carrying out a sentiment analysis from social surveys, using RStudio and Python to apply to several open-source datasets, which included the 2018 Social Indicators Survey dataset published by the City of Melbourne (CoM) and the Casey Next short survey 2016 datasetpublished by the city of Casey (CoC).
RETRACTED ARTICLE: Integrated CNN- and LSTM-DNN-based sentiment analysis over big social data for opinion mining
We, the Editors and Publisher of the journal Behaviour & Information Technology, have retracted the following article which was part of the Special Issue on Behaviour Monitoring and Management of
A Crowdsourcing Based Framework for Sentiment Analysis
TLDR
The key novelty of this approach is the new layer of validity check using a crowdsourcing component that ensures that the results obtained from social media are supported by opinions extracted directly from real-life consumers.
Crowd Sourcing as an Improvement of N-Grams Text Document Classification Algorithm
TLDR
This work deals with classification of text documents and its improvement through crowdsourcing, which aims to design and implement text documents classifier prototype based on documents similarity and to design evaluation and crowdsourcing-based classification improvement mechanism.
A deep learning classifier for sentence classification in biomedical and computer science abstracts
TLDR
A novel deep learning approach based on a convolutional layer and a bidirectional gated recurrent unit to classify sentences of abstracts to support scientific database querying, to summarize relevant literature works and to assist in the writing of new abstracts is proposed.
Detection of Types of Mental Illness through the Social Network Using Ensembled Deep Learning Model
TLDR
The proposed ensemble model used for performing the multiclass classification has performed better than the other models, with an accuracy greater than 92% in predicting the class.
Using Data Sciences in Digital Marketing: Framework, methods, and performance metrics
Higher Educational Establishments in Social Media: an Analytical Review
TLDR
The content analysis of higher educational establishments’ official web pages on Facebook and Instagram social nets as well as their promotional role in creating a definite image of a school are presented.
...
1
2
...

References

SHOWING 1-10 OF 67 REFERENCES
Feature extraction for tweet classification: Do the humans perform better?
TLDR
It is argued that tokens used by humans for sentiment analysis of tweets are probably the best feature set one can use for that purpose, and several automatically extracted features are compared with the features used for tweet classification, under a machine learning framework.
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
TLDR
This paper shows how to automatically collect a corpus for sentiment analysis and opinion mining purposes and builds a sentiment classifier, that is able to determine positive, negative and neutral sentiments for a document.
Feature Extraction for Sentiment Classification on Twitter Data
TLDR
A novel approach for automatically classifying the sentiment of “tweets” into positive, negative and neutral sentiment is introduced.
Social Media Mining: An Introduction
TLDR
Social Media Mining introduces the unique problems arising from social media data and presents fundamental concepts, emerging issues, and effective algorithms for network analysis and data mining.
Automatic Crowdsourcing-Based Classification of Marketing Messaging on Twitter
TLDR
It is demonstrated that a reasonably effective classifier can be created to identify the informative nature of Tweets based on crowd sourced training data, and results for identifying persuasive and transformative content are presented.
Learning Word Vectors for Sentiment Analysis
TLDR
This work presents a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content, and finds it out-performs several previously introduced methods for sentiment classification.
Lsislif: Feature Extraction and Label Weighting for Sentiment Analysis in Twitter
TLDR
This paper describes the sentiment analysis systems which have been built for SemEval2015 Task 10 Subtask B and E and presents their participation in Subtask E in which the system has got the second rank with Kendall metric but the first one with Spearman for ranking twitter terms according to their association with the positive sentiment.
Impact of Feature Selection Techniques for Tweet Sentiment Classification
TLDR
This work extensively studies the impact of ten filter-based feature selection techniques on classification performance, using ten feature subset sizes and four different learners to demonstrate that feature selection can significantly improve classification performance in comparison to not using feature selection.
Robust Sentiment Detection on Twitter from Biased and Noisy Data
In this paper, we propose an approach to automatically detect sentiments on Twitter messages (tweets) that explores some characteristics of how tweets are written and meta-information of the words
Automatic vs. Crowdsourced Sentiment Analysis
TLDR
The findings show that the crowdsourced sentiment analysis in both paid and volunteer-based platforms are considerably more accurate than the automatic sentiment analysis algorithm but still fail to achieve high accuracy compared to the manual method.
...
1
2
3
4
5
...