A reliable sentiment analysis for classification of tweets in social networks

AminiMotlagh, Masoud; Shahhoseini, Hadi Shahriar; Fatehi, Nina

doi:10.1007/s13278-022-00998-2

Cited by 22 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For classification purposes, these rules separate data points into different classes. Predictions for class labels are made based on the majority of examples that reached each leaf node during the tree's construction [1].…”

Section: Decision Tree Classifiermentioning

confidence: 99%

“…Social networks like Twitter are rapidly growing, allowing people to share personal opinions and emotions. This rapid growth and data accessibility offer research potential for various applications, including customer, product, sector, and digital marketing [1]. The increasing prevalence of interactions with products, articles, and our friends' posts in the digital age underscores the growing importance of studying semantic analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

WITHDRAWN: ChatGptTweets Analyses Based On AI

Author,

Author

et al. 2024

Preprint

View full text Add to dashboard Cite

Sentiment analysis plays a crucial role in understanding public opinions and attitudes. In this study, we address the sentiment analysis of ChatGPT tweets, leveraging a diverse set of machine learning models. The dataset comprises user-generated tweets directed at ChatGPT, reflecting a spectrum of sentiments ranging from positive endorsements to negative critiques. Sentiment analysis is the process of utilizing text analysis tools to extract and classify sentiments conveyed in text data. As demonstrated by past research, sentiment analysis of conversational agent interactions, such as those with ChatGPT, has a great deal of potential to offer insightful information to help developers and users understand the perception and effectiveness of these agents. This understanding contributes to improving user experience and refining the capabilities of conversational agents like ChatGPT. For sentiment analysis in this context, the current systems either use a learning-based method or a lexicon-based approach. While lexicon-based techniques tend to be domain-specific, limiting their wide application, learning-based techniques require annotated data. In order to get better results, this research adopts a hybrid method that combines lexicon-based and learning-based strategies. General-purpose lexicons of sentiment are used, and the tweets are annotated using tools such as Text Blob. Moreover, term frequency-inverse document frequency (TF-IDF), a feature engineering technique, has been included to extract important features. Ultimately, the sentiments of the tweets are classified using a variety of learning models, such as Machine Learning with logistic regression (LR), random forest (RF), decision tree (DT), gradient boosting (GB), and multilayer perceptron (MLP). The suggested hybrid approach's effectiveness is assessed using the F1-score, accuracy, precision, and recall metrics. According to experimental findings, combining lexicon-based and learning-based strategies yields better outcomes than each one used alone. Additionally, Text Blob has demonstrated encouraging results, with 99 percent accuracy achieved with MLP.

show abstract

Section: Decision Tree Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

WITHDRAWN: ChatGptTweets Analyses Based On AI

Author,

Author

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In a study by Masoud et al [1], data from two distinct datasets with different characteristics underwent analysis using four classification algorithms and ensemble techniques to enhance reliability. Surprisingly, the tests revealed that the use of a single algorithm slightly outperformed ensemble techniques.…”

Section: Literature Surveymentioning

confidence: 99%

Twitter Sentiment Analysis using Machine Learning Algorithms: A Comparative Analysis

Singh,

Kulshrestha,

Sinha

et al. 2024

Advancements in Communication and Systems

View full text Add to dashboard Cite

Data posted by people, or the users of a particular social network, has increased dramatically due to the changing behavior of various social networking sites like Instagram, Twitter, Snapchat, etc. Innumerable millions and billions of bytes of audio, video, and text are uploaded daily. This is because millions of people use a particular website. These folks are interested in sharing their thoughts and opinions on any topic they choose. People also want to know if most people will see an incident favorably, unfavorably, or neutrally. In this paper, the data is classified into Positive, Negative, or Neutral opinions, and it presents a detailed survey of Sentiment analysis of Twitter data using various Machine learning algorithms like Naïve Bayes, Support Vector Machine (SVM), Logistic regression, and decision tree. Additionally, the accuracy and F1 scores of the aforementioned algorithms are examined on two distinct Twitter datasets, and a comparison is made between the algorithms respective accuracies in the two datasets

show abstract

“…It also reduces the error generated by a single classifier, namely overfitting. Recently, in the literature, classifier ensemble has been used in areas such as disease detection [6], social networks [7] and mood recognition [8]. In these articles, the authors adopted a classifier ensemble for the current context, which yielded good results.…”

Section: Classifier Ensembles and Choquet Integralsmentioning

confidence: 99%

New Classifier Ensemble and Fuzzy Community Detection Methods Using POP Choquet-like Integrals

Zhang,

Jiang,

Wang

2023

Fractal Fract

View full text Add to dashboard Cite

Among various data analysis methods, classifier ensemble (data classification) and community network detection (data clustering) have aroused the interest of many scholars. The maximum operator, as the fusion function, was always used to fuse the results of the base algorithms in the classifier ensemble and the membership degree of nodes to classes in the fuzzy community. It is vital to use generalized fusion functions in ensemble and community applications. Since the Pseudo overlap function and the Choquet-like integrals are two new fusion functions, they can be combined as a more generalized fusion function. Along this line, this paper presents new classifier ensemble and fuzzy community detection methods using a pseudo overlap pair (POP) Choquet-like integral (expressed as a fraction). First, the pseudo overlap function pair is proposed to replace the product operator of the Choquet integral. Then, the POP Choquet-like integrals are defined to perform the combinatorial step of ensembles of classifiers and to generalize the GN modularity for the fuzzy community network. Finally, two new algorithms are designed for experiments, and some computational experiments with other algorithms show the importance of POP Choquet-like integrals. All of the experimental results show that our algorithms are practical.

show abstract

A reliable sentiment analysis for classification of tweets in social networks

Cited by 22 publications

References 27 publications

WITHDRAWN: ChatGptTweets Analyses Based On AI

WITHDRAWN: ChatGptTweets Analyses Based On AI

Twitter Sentiment Analysis using Machine Learning Algorithms: A Comparative Analysis

New Classifier Ensemble and Fuzzy Community Detection Methods Using POP Choquet-like Integrals

Contact Info

Product

Resources

About