Framework for Improved Sentiment Analysis via Random Minority Oversampling for User Tweet Review Classification

Almuayqil, Saleh Naif; Humayun, Mamoona; Jhanjhi, N. Z.; Almufareh, Maram Fahaad; Javed, Danish

doi:10.3390/electronics11193058

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study's contribution lies in the exploration of neural networks in the context of sentiment analysis and sets the stage for further investigations into optimal hyperparameter con gurations. [33] (out of which [22[ [25[ [27] were based on covid data and [24] was based on use of hashtags)…”

Section: Inclusion Criteriamentioning

confidence: 99%

See 1 more Smart Citation

Tweet Analysis: Visualisation using Python

Bhagat,

Bhandari,

Bharti

et al. 2024

Preprint

View full text Add to dashboard Cite

Most of the information is open to the public and can be mined. Huge amounts of data are available on the social networking site like Twitter. This data may be unstructured, semi-structured, or structured in any combination. This enables users to discuss concerns with various communities, as well as to share and express their opinions about various subjects. Sentiment analysis of Twitter data has been the subject of extensive research. Sentiment: that describes how people feel or think about a specific subject. Not facts, but subjective perceptions of the domain are the result. Twitter is one of the most widely used platforms. Many scholars who conduct research in critical domains such as consumer brands, market performance, and democratic election prediction have found inspiration from Twitter. The initiative focuses on Twitter data analysis. This paper focuses on a tool to assess public sentiment, monitor crises, conduct market research, and the influence and reach of a Twitter trend, it lets users view a range of metrics related to any hashtag, such as the most popular users utilizing it, users with the greatest reach, an estimate of the hashtag's actual and maximum reach, the timely frequency of tweets and retweets, and the estimated market value of the hashtag with the use of python and Twitter API. It will help combat misinformation and online negativity and promote accountability with a focus on visual content analysis.

show abstract

Section: Inclusion Criteriamentioning

confidence: 99%

“…After making the implementation model using python and connecting it with the X API. [24] The libraries used were Pandas, Tweepy, NetworlX, Ndlib and Matplotlib. Generating the results by only considering a speci c hashtag which is #kashmir the following results are observed.…”

Section: Applying Twitter Datamentioning

confidence: 99%

Tweet Analysis: Visualisation using Python

Bhagat,

Bhandari,

Bharti

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Smart appliances can monitor users' electricity consumption, adjust temperature based on ambiance, and enable remote management of various appliances via mobile devices. Smart Environment: The use of IoT can revolutionize environmental strategies, from monitoring air quality and traffic management in cities to assessing water pollution (Pratomo, 2023;Almuayqil, S. N et al, 2022). Additionally, IoT aids in waste management by monitoring and reducing industrial pollutants.…”

Section: 2mentioning

confidence: 99%

Innovations in Security: A Study of Cloud Computing and IoT

Azam,

Tajwar,

Mayhialagan

et al. 2023

IJEMD-CSAI

View full text Add to dashboard Cite

Cloud computing and IoT security are pivotal technologies that have reshaped the IT landscape. Leading tech giants like Google, Microsoft, and Amazon have harnessed their potential, continually enhancing these services. Despite their increasing user bases, these technologies face significant hurdles, with security emerging as the foremost challenge. This paper delves into the security aspects of both cloud computing and IoT services, encompassing security components, processes, threats, and real-world examples of security-related technologies. We also explore the impacts, including benefits, limitations, and future potential of cloud computing and IoT security services. In our exploration, we define cloud computing and the Internet of Things (IoT) to provide a foundational understanding of these technologies. We then investigate their real-world applications, highlighting their relevance and ubiquity in various domains. The core of this paper revolves around the discussion of security issues in cloud computing and IoT. For IoT, we dissect security components, processes, and threats, offering real-world technology examples to illustrate their significance. Similarly, for cloud computing, we delve into its security components, processes, and threats while showcasing practical applications of security technologies. The impact section assesses the benefits of cloud computing and IoT security. It also candidly addresses issues, limitations, and challenges associated with these technologies, offering insights into potential future advancements. This comprehensive study underscores the significance of security in the domains of cloud computing and IoT, offering a valuable resource for both practitioners and researchers. As these technologies continue to evolve, understanding their security implications is crucial for harnessing their full potential.

show abstract

“…The datasets are often highly imbalanced and required a long processing time when classification tasks such as sentiment analysis are involved [23]. The oversampling technique is the most explored, but under-sampling is often disregarded [24]. Therefore, a comprehensive model is necessary to address these issues.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

Self Cite

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

Framework for Improved Sentiment Analysis via Random Minority Oversampling for User Tweet Review Classification

Cited by 12 publications

References 34 publications

Tweet Analysis: Visualisation using Python

Tweet Analysis: Visualisation using Python

Innovations in Security: A Study of Cloud Computing and IoT

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

Contact Info

Product

Resources

About