Imbalanced Twitter Sentiment Analysis using Minority Oversampling

Ghosh, Kushankur; Banerjee, Arghasree; Chatterjee, Sankhadeep; Sen, Soumya

doi:10.1109/icawst.2019.8923218

Cited by 32 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the thematic analysis, we also used tweets from personal accounts that mentioned Vessel and suicide in the first 14 days after each suicide case. Because of the imbalanced number of tweets across the four cases, we followed the previously used process of oversampling minorities [ 20 ]. We over-sampled the tweets for the first two cases and under-sampled the tweets for the third and fourth cases due to the different volumes of data in the earlier (first and second) and later stages (third and fourth).…”

Section: Methodsmentioning

confidence: 99%

Social Media Sentiments on Suicides at the New York City Landmark, Vessel: A Twitter Study

Yip

Xiao

et al. 2022

IJERPH

View full text Add to dashboard Cite

Vessel is a landmark created by Heatherwick Studio where visitors can enjoy views of New York City from different heights and perspectives. However, between February 2020 and July 2021, four individuals jumped to their deaths from the landmark. Effective preventive solutions have yet to be identified, and the site is currently closed. In this study, we examined the trajectory of public sentiment on the suicide-related activity at Vessel on Twitter by investigating the engagement patterns and identifying themes about the four suicides from February 2020 to August 2021 (n = 3058 tweets). The results show increased levels of discussion about each successive suicide case in the first 14 days following each incident (from 6 daily tweets for the first case to 104 for the fourth case). It also took longer for relevant discussions to dissipate (4 days for the first and 14 days for the fourth case, KS statistic = 0.71, p < 0.001). Thematic analysis shows a shift from expressions of emotion to urging suicide prevention actions in the third and fourth cases; additionally, we detected growing support for restricting means. We suggest that, prior to the reopening of Vessel, collective efforts should be made to install safety protections and reduce further suicide risks.

show abstract

Section: Methodsmentioning

confidence: 99%

Social Media Sentiments on Suicides at the New York City Landmark, Vessel: A Twitter Study

Yip

Xiao

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…None [28] In opinion mining, real user tweets were utilized to systematically check the impact of class inequality problem.…”

Section: Purposementioning

confidence: 99%

Enhancing Sentiment Analysis via Random Majority Under-Sampling with Reduced Time Complexity for Classifying Tweet Reviews

et al. 2022

View full text Add to dashboard Cite

Twitter has become a unique platform for social interaction from people all around the world, leading to an extensive amount of knowledge that can be used for various reasons. People share and spread their own ideologies and point of views on unique topics leading to the production of a lot of content. Sentiment analysis is of extreme importance to various businesses as it can directly impact their important decisions. Several challenges related to the research subject of sentiment analysis includes issues such as imbalanced dataset, lexical uniqueness, and processing time complexity. Most machine learning models are sequential: they need a considerable amount of time to complete execution. Therefore, we propose a model sentiment analysis specifically designed for imbalanced datasets that can reduce the time complexity of the task by using various text sequenced preprocessing techniques combined with random majority under-sampling. Our proposed model provides competitive results to other models while simultaneously reducing the time complexity for sentiment analysis. The results obtained after the experimentation corroborate that our model provides great results producing the accuracy of 86.5% and F1 score of 0.874 through XGB.

show abstract

“…Imbalance data is the most common thing in sentiment analysis [32]. Data imbalance is a situation where the data ratio is not proportional or unbalanced, causing the performance of the model application to be ineffective [33].…”

Section: Introductionmentioning

confidence: 99%

Dealing imbalance dataset problem in sentiment analysis of recession in Indonesia

Kristiyanti,

Sanjaya,

Tjokro

et al. 2024

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Global recession news dominates social media, particularly in Indonesia, with social news platforms on Twitter generating public responses and <br /> re-tweetings on the issue. Mining these opinions from Twitter using a sentiment analysis approach yields invaluable insights. The research stages included data collection, pre-processing, data labeling using the <br /> lexical-based method like valence aware dictionary and sentiment reasoner (VADER) and TextBlob, sampling techniques using synthetic minority oversampling technique (SMOTE) and random over sampling (ROS) before and after splitting data, and modeling using machine learning such as support vector machines (SVM), k-nearest neighbour (KNN), naive Bayes, and model evaluation. The problem is that almost 300,000 data collected from NodeXL are unbalanced. The findings show that models with balanced datasets show better model evaluation results. The sampling technique was carried out before and after splitting the data. The model evaluation results show that the Bernoulli-naive Bayes algorithm, with the VADER labeling technique, and the SMOTE sampling technique after splitting data, obtains the best accuracy of 84%, and using the ROS technique obtains an accuracy of 81%. On the other hand, with the SMOTE and ROS technique before splitting data on the SVM algorithm, it gets the best accuracy of 93% from before if only using SVM only reached 84%.</span>

show abstract

Imbalanced Twitter Sentiment Analysis using Minority Oversampling

Cited by 32 publications

References 17 publications

Social Media Sentiments on Suicides at the New York City Landmark, Vessel: A Twitter Study

Social Media Sentiments on Suicides at the New York City Landmark, Vessel: A Twitter Study

Enhancing Sentiment Analysis via Random Majority Under-Sampling with Reduced Time Complexity for Classifying Tweet Reviews

Dealing imbalance dataset problem in sentiment analysis of recession in Indonesia

Contact Info

Product

Resources

About