Comparative Study of Classification Algorithms to Analyze and Predict a Twitter Sentiment in Apache Spark

Albaldawi, Wafaa S.; Almuttairi, Rafah M.

doi:10.1088/1757-899x/928/3/032045

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After crossing each layer of the neural networks, the sentiment model returns the emotion of the social media text data, detecting whether each contained tweet shows a positive or a negative sentiment. The presented model gave an accuracy of 84.97%, surpassing other existing models for this purpose (Rustam et al 2019;Albaldawi and Almuttairi 2020).…”

Section: Sentiment Analysis (Rq-4)mentioning

confidence: 68%

Nuclear energy: Twitter data mining for social listening analysis

Bilbao

Jaca-Madariaga

Belver

et al. 2023

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Knowing the presence, attitude and sentiment of society is important to promote policies and actions that influence the development of different energy sources and even more so in the case of an energy source such as nuclear, which has not been without controversy in recent years. The purpose of this paper was to conduct a social listening analysis of nuclear energy using Twitter data mining. A total of 3,709,417 global tweets were analyzed through the interactions and emotions of Twitter users throughout a crucial year: 6 months before and 6 months after the beginning of Russian invasion of Ukraine and the first attack on the Zaporizhzhia NPP. The research uses a novel approach to combine social network analysis methods with the application of artificial neural network models. The results reveal the digital conversation is influenced by the Russian invasion of Ukraine. However, tweets containing personal opinions of influential people also manage to enter the digital conversation, defining the magnitude and direction of the debate. The digital conversation is not constructed as a public argument. Generally, it is a conversation with non-polarized communities (politics, business, science and media); neither armed conflict or military threats against Zaporizhzhia NPP succeed in rousing anti-nuclear voices, even though these events do modify the orientation of the sentiment in the language used, making it more negative.

show abstract

Section: Sentiment Analysis (Rq-4)mentioning

confidence: 68%

Nuclear energy: Twitter data mining for social listening analysis

Bilbao

Jaca-Madariaga

Belver

et al. 2023

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…Research topics in social psychology covered in the past studies include the relationship between trust and the presence of infectious disease [70]; psychological needs and their satisfaction level during the pandemic [71]; the effect of fear and collectivism on the public prevention against COVID-19 [72]; peoples' preferences to protect the environment they live in [73]. Some of the harmful effects of the pandemic have been studied, including family violence [21], increasing racial sentiment toward Asian people [23], the emergence of incivility and fake news on social media [74,29], and emotional tendency and emotional symptoms of mental disorder facing the outbreak [75,76].…”

Section: Social Lifementioning

confidence: 99%

“…Apache Kafka is an open-source streaming platform in the middle layer that separates data streams and transmits them in real-time to Hadoop big data lakes, applications, and systems analysis. Kafka is usually used for data streaming, website activity tracking, and real-time analytics, as was done by Albadawi [21] and Zhang X et al [58] in their study on analyzing Twitter data. Analysis of the needs of the distribution system operator for the electricity grid [110].…”

Section: Data Source and Datasetmentioning

confidence: 99%

“…Big data offers a solution to analyze human mobility and their contact data to identify confirmed cases and locations that the coronavirus may contaminate. Big data analysis on social media related to COVID-19 contributes to solving social life problems in gaining opinion, concern, and public response to the policies implemented [21,22,23]. Moreover, big data applications have benefited the quality of care by accelerating disease detection and providing better health care services to patients [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Big Data Research in Fighting COVID-19: Contributions and Techniques

Riswantini

Nugraheni

Munandar

et al. 2021

Preprint

View full text Add to dashboard Cite

COVID-19 has induced many problems in various sectors of life for humanity around the world. After one year of pandemic, many studies have been carried out in exposing various technology innovations and applications to combat the coronavirus that has killed more people than most. The pandemic has accelerated the use of Big Data technology to mitigate the threats of COVID-19. This survey aims to explore the Big Data research for COVID-19. We collected and analyzed the relevant academic articles to identify how Big Data technology can cover the challenges faced in overcoming the pandemic. In determining the research areas addressed by the past studies, we highlight the technology contributions to five major areas of healthcare, social life, government policy, business and management, and the environment. We discuss how analytical techniques of machine learning, deep learning, statistics, and mathematics can solve pandemic issues. The Big Data research for COVID-19 used a wide variety of data sources available publicly or privately. At the end of the discussion, we present the data source used in the past studies encompassing government official data, institutional service data, IoT generated data, online media data, and open data. We hope that this survey will clarify the role of Big Data technology in enhancing the research for COVID-19.

show abstract