SentiMI: Introducing point-wise mutual information with SentiWordNet to improve sentiment polarity detection

Khan, Farhan Hassan; Qamar, Usman; Bashir, Saba

doi:10.1016/j.asoc.2015.11.016

Cited by 81 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent research from Hasan [5] provides us with an integrated approach based on sentiment analyzer and machine learning. For the sentiment analyzer, the author considered the TextBlob [9], a customized Word Sense Disambiguation (W-WSD) [10] and The SentiWordNet [11] for comparison. For the classifier, the author leverages the Waikato Environment for Knowledge Analysis (WEKA) [12] software to deliver the classification based on the calculated polarity and subjectivity, using Naïve Bayes Classifier (NBC) [13] and Support Vector Machine (SVM) [14].…”

Section: Related Work Regarding Twitter Sentiment Analysismentioning

confidence: 99%

A Novel Method for Twitter Sentiment Analysis Based on Attentional-Graph Neural Network

Wang

2020

Information

View full text Add to dashboard Cite

Twitter sentiment analysis is an effective tool for various Twitter-based analysis tasks. However, there is still no neural-network-based research which takes both the tweet-text information and user-connection information into account. To this end, we propose the Attentional-graph Neural Network based Twitter Sentiment Analyzer (AGN-TSA), a Twitter sentiment analyzer based on attentional-graph neural networks. AGN-TSA fuses the tweet-text information and the user-connection information through a three-layered neural structure, which includes a word-embedding layer, a user-embedding layer and an attentional graph network layer. For the training of AGN-TSA, dedicated loss functions are designed for the structural controllability of AGN-TSA network. Experiments based on real-world dataset concerning the 2016 presidential election of America exhibit that AGN-TSA is superior under multiple metrics over several prevailing methods, with a performance boost of over 5%. The empirical settings of parameters are given based on extensive rotation experiments.

show abstract

Section: Related Work Regarding Twitter Sentiment Analysismentioning

confidence: 99%

A Novel Method for Twitter Sentiment Analysis Based on Attentional-Graph Neural Network

Wang

2020

Information

View full text Add to dashboard Cite

show abstract

“…It is derived from WordNet. Each synset (noun, verb, adjective, and adverb) in SentiWordNet is assigned three types of sentiment scores (polarity) namely, positivity Pos(S) , negativity Neg(S) , and objectivity Obj(S) , ranged in the [0, 1] interval and in sum equal to 1.0 . WordNet is a “dictionary of meaning” integrating the functions of dictionaries and thesauruses.…”

Section: Background Knowledge and Related Workmentioning

confidence: 99%

“…The construction of this dictionary is based on SentiWordNet 0.3 . and WOLF 0.6 : DICO is composed of Synsets from WOLF 0.6 with their respective polarities obtained from SentiWordNet 0.3. The following assumptions were made in the construction of this DICO sentiment lexicon: First, the sense of the word in the two languages was assumed to be the same.…”

Section: Educational Guidance Process Based On Opinion Mining—opinormentioning

confidence: 99%

Educational guidance process integrating opinion mining

Lazib

Bouarab-Dahmani

Haddadi

2019

Comp Applic In Engineering

View full text Add to dashboard Cite

Opinion mining is a fast-developing field of study with numerous applications.It raises economic and political interests, especially in decision-making processes. In this paper, we are interested in educational opinion mining. We propose an educational guidance process that aims to improve university orientation after the secondary school cycle. Unlike the ordinary orientation processes, our process integrates the opinions of pupil, parents, and teachers, collected periodically. These opinions are treated to sort out the studies' domains in a positive polarity order. An orientation score is then calculated based on these opinions, the student's aptitudes and the continuous evaluation marks to guide pupils toward the most favourable discipline. The experimentations conducted on a sample of pupils (300) give a better convergence to the pupils' explicit choices using our proposal with a κ coefficient of 0.71, against 0.29 using only marks. K E Y W O R D Seducational guidance, opinion mining, opinion mining for education, opinion synthesis, pupil's opinions

show abstract

“…Devaraj et al [15] detect sentiment polarity of free-form texts by using lexicon ensemble and lexicon pooling. Khan et al [16] build a sentiment dictionary SentiMI by extracting sentiment terms from SentiWordNet and develop a complete framework using feature selection and extracting mutual information from SentiWordNet to improve sentiment polarity detection.…”

Section: Sentiment Polarity Detectionmentioning

confidence: 99%

Review Rating Prediction on Location-Based Social Networks Using Text, Social Links, and Geolocations

Wang

Zhong

Yang

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Review rating prediction is an important problem in machine learning and data mining areas and has attracted much attention in recent years. Most existing methods for review rating prediction on Location-Based Social Networks only capture the semantics of texts, but ignore user information (social links, geolocations, etc.), which makes them less personalized and brings down the prediction accuracy. For example, a user's visit to a venue may be influenced by their friends' suggestions or the travel distance to the venue. To address this problem, we develop a review rating prediction framework named TSG by utilizing users' review Text, Social links and the Geolocation information with machine learning techniques. Experimental results demonstrate the effectiveness of the framework.

show abstract

SentiMI: Introducing point-wise mutual information with SentiWordNet to improve sentiment polarity detection

Cited by 81 publications

References 12 publications

A Novel Method for Twitter Sentiment Analysis Based on Attentional-Graph Neural Network

A Novel Method for Twitter Sentiment Analysis Based on Attentional-Graph Neural Network

Educational guidance process integrating opinion mining

Review Rating Prediction on Location-Based Social Networks Using Text, Social Links, and Geolocations

Contact Info

Product

Resources

About