SentiTFIDF – Sentiment Classification using Relative Term Frequency Inverse Document Frequency

Ghag, Kranti; Shah, Ketan

doi:10.14569/ijacsa.2014.050206

Cited by 25 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another work of Kaewpitakkun et al [27], also found that reevaluating the objective words in SentiWordNet would improve the accuracy of sentiment classification. The same conclusion was reached by Amiri and Chua [28] and Ghang and Shah [29] in their work.…”

Section: Relatedworksupporting

confidence: 87%

Using Objective Words in the Reviews to Improve the Colloquial Arabic Sentiment Analysis

Al-Harbi¹

2017

IJNLC

View full text Add to dashboard Cite

One of the main difficulties in sentiment analysis of the Arabic language is the presence of the colloquialism. In this paper, we examine the effect of using objective words in conjunction with sentimental words on sentiment classification for the colloquial Arabic reviews, specifically Jordanian colloquial reviews. The reviews often include both sentimental and objective words; however, the most existing sentiment analysis models ignore the objective words as they are considered useless. In this work, we created tow lexicons: the first includes the colloquial sentimental words and compound phrases, while the other contains the objective words associated with values of sentiment tendency based on a particular estimation method. We used these lexicons to extract sentiment features that would be training input to the Support Vector Machines (SVM) to classify the sentiment polarity of the reviews. The reviews dataset have been collected manually from JEERAN website. The results of the experiments show that the proposed approach improves the polarity classification in comparison to two baseline models, with accuracy 95.6%.

show abstract

Section: Relatedworksupporting

confidence: 87%

Using Objective Words in the Reviews to Improve the Colloquial Arabic Sentiment Analysis

Al-Harbi¹

2017

IJNLC

View full text Add to dashboard Cite

show abstract

“…Furthermore, it would be a reasonable idea to utilize further machine learning algorithms such as naive bayes or random forest, which are not based on word embeddings but on term frequency times inverse document frequency vectors to extend the systematic comparison and test which combined approaches offer more accurate results. It does not require word embedding but is also used for SA [6,9]. While word embedding links the semantics of sentences, term frequency times inverse document frequency computes the importance of a term inside a comment by their frequency of the entire dataset.…”

Section: Further Researchmentioning

confidence: 99%

Identifying Political Sentiments on YouTube: A Systematic Comparison Regarding the Accuracy of Recurrent Neural Network and Machine Learning Models

Röchert

Neubaum

Stieglitz

2020

Disinformation in Open Online Media

View full text Add to dashboard Cite

Since social media have increasingly become forums to exchange personal opinions, more and more approaches have been suggested to analyze those sentiments automatically. Neural networks and traditional machine learning methods allow individual adaption by training the data, tailoring the algorithm to the particular topic that is discussed. Still, a great number of methodological combinations involving algorithms (e.g., recurrent neural networks (RNN)), techniques (e.g., word2vec), and methods (e.g., Skip-Gram) are possible. This work offers a systematic comparison of sentiment analytical approaches using different word embeddings with RNN architectures and traditional machine learning techniques. Using German comments of controversial political discussions on YouTube, this study uses metrics such as F1-score, precision and recall to compare the quality of performance of different approaches. First results show that deep neural networks outperform multiclass prediction with small datasets in contrast to traditional machine learning models with word embeddings.

show abstract

“…Unlike TFIDF mentioned above, this study divides data into two parts, one for positive data, and one for negative. Furthermore, according to K. Ghag, K. Shah [17], SentiTFIDF was applied to this project to classify the positive, negative and neutral emotional mood. If the term positive is larger than the term of negative, the term is classified as positive.…”

Section: Fig3 Example Sentencementioning

confidence: 99%

The Awareness of Environment Conservation Based on Opinion Data Mining From Social Media

Kularbphettong¹

2019

GEOMATE

View full text Add to dashboard Cite

Social media has become an important role in society and people widely use social media platforms to express and criticize their opinion. With the previous studies, there is much research to develop and harvest information and knowledge from social media data for decision making and prediction. The awareness of environmental conservation has become a significant issue nowadays and building and raising environmental awareness is to conserve and protect nature for the benefits of humans. Opinion mining is one of text mining approaches to assess the attitude in a given subject and the attitude may be positive or negative opinion. The paper proposes to conduct social media opinion mining in case of the awareness of environment conservation of Thai people. This study shows that social media effects to build and raise the awareness of environment protection and furthermore this research can apply to other fields and industries aspects as well.

show abstract

SentiTFIDF – Sentiment Classification using Relative Term Frequency Inverse Document Frequency

Cited by 25 publications

References 27 publications

Using Objective Words in the Reviews to Improve the Colloquial Arabic Sentiment Analysis

Using Objective Words in the Reviews to Improve the Colloquial Arabic Sentiment Analysis

Identifying Political Sentiments on YouTube: A Systematic Comparison Regarding the Accuracy of Recurrent Neural Network and Machine Learning Models

The Awareness of Environment Conservation Based on Opinion Data Mining From Social Media

Contact Info

Product

Resources

About