Study of Twitter Sentiment Analysis using Machine Learning Algorithms on Python

International Journal of Computer Applications, Journal Year: 2017, Volume and Issue: 165(9), P. 29 - 34

Published: May 17, 2017

Twitter is a platform widely used by people to express their opinions and display sentiments on different occasions.Sentiment analysis an approach analyze data retrieve sentiment that it embodies.Twitter application of from (tweets), in order extract conveyed the user.In past decades, research this field has consistently grown.The reason behind challenging format tweets which makes processing difficult.The tweet very small generates whole new dimension problems like use slang, abbreviations etc.In paper, we aim review some papers regarding Twitter, describing methodologies adopted models applied, along with generalized Python based approach.

Language: Английский

---

Advances in Sentiment Analysis - Techniques, Applications, and Challenges

Artificial intelligence, Journal Year: 2023, Volume and Issue: unknown

Published: Sept. 29, 2023

This cutting-edge book brings together experts in the field to provide a multidimensional perspective on sentiment analysis, covering both foundational and advanced methodologies. Readers will gain insights into latest natural language processing machine learning techniques that power enabling extraction of nuanced emotions from text.
Key Features:
•State-of-the-Art Techniques: Explore most recent advancements deep approaches lexicons beyond.
•Real-World Applications: Dive wide range applications, including social media monitoring, customer feedback sentiment-driven decision-making.
•Cross-Disciplinary Insights: Understand how analysis influences is influenced by fields such as marketing, psychology, finance.
•Ethical Privacy Considerations: Delve ethical challenges privacy concerns inherent with discussions responsible AI usage.
•Future Directions: Get glimpse future emerging trends unresolved challenges.
an essential resource for researchers, practitioners, students like processing, learning, data science. Whether you're interested understanding sentiment, monitoring trends, or advancing state art, this equip you knowledge tools need navigate complex landscape analysis.

Language: Английский

---

Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches

International Journal on Recent and Innovation Trends in Computing and Communication, Journal Year: 2023, Volume and Issue: 11(5s), P. 118 - 138

Published: May 17, 2023

Sentiment analysis (SA) is also known as opinion mining, it the process of gathering and analyzing people's opinions about a particular service, good, or company on websites like Twitter, Facebook, Instagram, LinkedIn, blogs, among other places. This article covers thorough SA its levels. manuscript's main focus aspect-based SA, which helps manufacturing organizations make better decisions by examining consumers' viewpoints their products. The many approaches methods used in sentiment are covered this review study (ABSA). features associated with aspects were manually drawn out traditional methods, made time-consuming error-prone operation. Nevertheless, these restrictions may be overcome artificial intelligence develops. Therefore, to increase effectiveness ABSA, researchers increasingly using AI-based machine learning (ML) deep (DL) techniques. Additionally, certain recently released ABSA based ML DL examined, contrasted, research, gaps both methodologies discovered. At conclusion study, difficulties that current models encounter emphasized, along suggestions can improve efficacy precision systems.

Language: Английский

---

Emotion-Semantic-Enhanced Neural Network

IEEE/ACM Transactions on Audio Speech and Language Processing, Journal Year: 2018, Volume and Issue: 27(3), P. 531 - 543

Published: Dec. 12, 2018

Although sentiment analysis on microblog posts has been studied in depth, of is still challenging because the limited contextual information that they normally contain. In environments, emoticons are frequently used and have clear emotional meanings. They important signals for sentimental analysis. Existing studies typically use as noisy labels or similar indicators to effectively train classifier but overlook their potentiality. We address this issue by constructing an space a feature representation matrix projecting words into based semantic composition. To improve performance analysis, we propose new emotion-semantic-enhanced convolutional neural network (ECNN) model. ECNN can emoticon embedding projection operator. By space, it help identify subjectivity, polarity, emotion environments. It more capable capturing than other models, so performance. The experimental results show model consistently outperforms models dataset several tasks. This paper provides insights design natural language processing

Language: Английский

---

Predicting depression using deep learning and ensemble algorithms on raw twitter data

International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering, Journal Year: 2020, Volume and Issue: 10(4), P. 3751 - 3751

Published: March 8, 2020

Social network and microblogging sites such as Twitter are widespread amongst all generations nowadays where people connect share their feelings, emotions, pursuits etc. Depression, one of the most common mental disorder, is an acute state sadness person loses interest in activities. If not treated immediately this can result dire consequences death. In era virtual world, more comfortable expressing emotions they have become a part parcel everyday lives. The research put forth thus, employs machine learning classifiers on twitter data set to detect if person’s tweet indicates any sign depression or not.

Language: Английский

---

Multi-level deep Q-networks for Bitcoin trading strategies

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Jan. 8, 2024

Abstract The Bitcoin market has experienced unprecedented growth, attracting financial traders seeking to capitalize on its potential. As the most widely recognized digital currency, holds a crucial position in global landscape, shaping overall cryptocurrency ecosystem and driving innovation technology. Despite use of technical analysis machine learning, devising successful trading strategies remains challenge. Recently, deep reinforcement learning algorithms have shown promise tackling complex problems, including profitable strategy development. However, existing studies not adequately addressed simultaneous consideration three critical factors: gaining high profits, lowering level risk, maintaining number active trades. In this study, we propose multi-level Q-network (M-DQN) that leverages historical price data Twitter sentiment analysis. addition, an innovative preprocessing pipeline is introduced extract valuable insights from data, which are then input into M-DQN model. A novel reward function further developed encourage model focus these factors, thereby filling gap left by previous studies. By integrating proposed technique with DQN, aim optimize decisions market. experiments, integration led noteworthy 29.93% increase investment value initial amount Sharpe Ratio excess 2.7 measuring risk-adjusted return. This performance significantly surpasses state-of-the-art aiming develop efficient strategy. Therefore, method makes contribution field

Language: Английский

---

Sentiment Analysis of Arabic Tweets in e-Learning

Journal of Computer Science, Journal Year: 2016, Volume and Issue: 12(11), P. 553 - 563

Published: Nov. 1, 2016

In this study, we present the design and implementation of Arabic text classification in regard to university students' opinions through different algorithms such as Support Vector Machine (SVM) Naive Bayes (NB). The aim study is develop a framework analyse Twitter "tweets" having negative, positive or neutral sentiments education or, other words, illustrate relationship between conveyed tweets learning experiences at universities. Two experiments were carried out, one using negative classes only with class. results show that Arabic, SVM an n-gram feature achieved higher accuracy than NB both

Language: Английский

---

Sentiment Analysis of Financial Textual data Using Machine Learning and Deep Learning Models

Informatica, Journal Year: 2023, Volume and Issue: 47(5)

Published: May 26, 2023

Recently, extensive research in the field of financial sentiment analysis has been conducted. Sentiment (SA) any text data denotes feelings and attitudes individual on particular topics or products. It applies statistical approaches with artificial intelligence (AI) algorithms to extract substantial knowledge from a huge amount data. This study extracts polarity (negative, positive, neutral) textual using machine learning deep algorithms. The constructed model used Multinomial Naïve Bayes (MNB) Logistic regression (LR) classifiers. On other hand, three have utilized which are Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), Gated Unit (GRU). results MNB LR obtained good very rate accuracy respectively. Likewise, RNN, LSTM GRU an excellent accuracy. can be concluded outcomes that preprocessing stages made positive impact rate.

Language: Английский

---

Sentiment evolution on social media: An in-depth study using Naive bayes for Twitter sentiment analysis

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3224, P. 020022 - 020022

Published: Jan. 1, 2025

Language: Английский

---

The Media Spatial Diffusion Effect and Distribution Characteristics of AI in Education: An Empirical Analysis of Public Sentiments Across Provincial Regions in China

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 3184 - 3184

Published: March 14, 2025

With the rapid integration of artificial intelligence (AI) technologies in field education, public sentiment towards this development has gradually emerged as an important area research. This study focuses on analysis online opinions regarding application AI education. Python was used to scrape relevant comments from various provinces China. Using SnowNLP algorithm, sentiments were classified into three categories: positive, neutral, and negative. The primarily analyzes spatial distribution characteristics positive negative sentiments, with a visualization results through Geographic Information Systems (GIS). Additionally, Moran’s I Getis-Ord Gi* are introduced detect autocorrelation attitudes. Furthermore, by constructing multivariable geographical detector model MGWR, explores impact factors such digital economy, construction smart cities, local government policy attention, literacy residents, level education infrastructure research will reveal regional disparities education-related its driving mechanisms, providing data support empirical references for optimizing

Language: Английский

---