Comparing Twitter Data for Topic Modling, Clustering, and Predictive Analysis Using LSTM Model

Md. Shamaun Islam () and Sadat Bin Shahid ()
Additional contact information
Md. Shamaun Islam: Chongqing University of PT
Sadat Bin Shahid: Hubei University of Technology

Chapter Chapter 28 in City, Society, and Digital Transformation, 2022, pp 375-392 from Springer

Abstract: Abstract Extraction topics to find the difference between the two datasets of information, as a rule, seems unused. Machine learning and the calculation of Natural language Process correction are used to analyze the ever-changing statistics of Twitter accessible online, including modelling processes for a longer time. Two datasets of content information were selected to evaluate comparisons based on specific statistical tests, such as quality and response, accuracy, and statistical tests for particular measurements, such as Portion F and Title. Twitter has become amongst the most often used online network site because anyone can easily publish information about their thoughts on a specific issue via a public message called a tweet. Twitter play an essential part in the prioritization of public life. It is necessary to know about the topic and domain on social media sites. This research work performs a topic modelling on Twitter data related to covid19. Two different data sets are discussed, and tweets are clustered through the k-mean clustering algorithm. Topics are also found in each cluster using the LDA technique. The clustered data sets are predictively analyzed through the LSTM model. The results show that the model achieves 96% accuracy.

Keywords: Deep convolutional neural networks; Transfer learning; K-means clustering; LDA; Topic modelling; Research trend (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-031-15644-1_28

Ordering information: This item can be ordered from
http://www.springer.com/9783031156441

DOI: 10.1007/978-3-031-15644-1_28

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().