scholarly journals Text Mining Approaches to Analyze Public Sentiment Changes Regarding COVID-19 Vaccines on Social Media in Korea

2021 ◽  
Vol 18 (12) ◽  
pp. 6549
Author(s):  
Jae-Geum Shim ◽  
Kyoung-Ho Ryu ◽  
Sung Hyun Lee ◽  
Eun-Ah Cho ◽  
Yoon Ju Lee ◽  
...  
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Time Course ◽  
Latent Dirichlet Allocation ◽  
Allocation Model ◽  
Public Response ◽  
Latent Dirichlet Allocation Model ◽  
Public Sentiment ◽  
Before And After

The COVID-19 pandemic has affected the entire world, resulting in a tremendous change to people’s lifestyles. We investigated the Korean public response to COVID-19 vaccines on social media from 23 February 2021 to 22 March 2021. We collected tweets related to COVID-19 vaccines using the Korean words for “coronavirus” and “vaccines” as keywords. A topic analysis was performed to interpret and classify the tweets, and a sentiment analysis was conducted to analyze public emotions displayed within the retrieved tweets. Out of a total of 13,414 tweets, 3509 were analyzed after preprocessing. Eight topics were extracted using the Latent Dirichlet Allocation model, and the most frequently tweeted topic was vaccine hesitation, consisting of fear, flu, safety of vaccination, time course, and degree of symptoms. The sentiment analysis revealed a similar ratio of positive and negative tweets immediately before and after the commencement of vaccinations, but negative tweets were prominent after the increase in the number of confirmed COVID-19 cases. The public’s anticipation, disappointment, and fear regarding vaccinations are considered to be reflected in the tweets. However, long-term trend analysis will be needed in the future.

scholarly journals Are Black Friday Deals Worth It? Mining Twitter Users’ Sentiment and Behavior Response

2019 ◽  
Vol 5 (3) ◽  
pp. 58 ◽  
Author(s):  
Saura ◽  
Reyes-Menendez ◽  
Palos-Sanchez
Keyword(s):  
Social Media ◽  
Text Mining ◽  
Latent Dirichlet Allocation ◽  
Allocation Model ◽  
Media Communication ◽  
Customer Support ◽  
Latent Dirichlet Allocation Model ◽  
Twitter Users ◽  
And Behavior ◽  
Black Friday

The Black Friday event has become a global opportunity for marketing and companies’ strategies aimed at increasing sales. The present study aims to understand consumer behavior through the analysis of user-generated content (UGC) on social media with respect to the Black Friday 2018 offers published by the 23 largest technology companies in Spain. To this end, we analyzed Twitter-based UGC about companies’ offers using a three-step data text mining process. First, a Latent Dirichlet Allocation Model (LDA) was used to divide the sample into topics related to Black Friday. In the next step, sentiment analysis (SA) using Python was carried out to determine the feelings towards the identified topics and offers published by the companies on Twitter. Thirdly and finally, a data-text mining process called textual analysis (TA) was performed to identify insights that could help companies to improve their promotion and marketing strategies as well as to better understand the customer behavior on social media. The results show that consumers had positive perceptions of such topics as exclusive promotions (EP) and smartphones (SM); by contrast, topics such as fraud (FA), insults and noise (IN), and customer support (CS) were negatively perceived by customers. Based on these results, we offer guidelines to practitioners to improve their social media communication. Our results also have theoretical implications that can promote further research in this area.

Exploring Public Response to COVID-19 on Weibo with LDA Topic Modeling and Sentiment Analysis

2020 ◽  
Vol 5 (1) ◽  
pp. 86-99
Author(s):  
Runbin Xie ◽  
Samuel Kai Wah Chu ◽  
Dickson Kak Wah Chiu ◽  
Yangshu Wang
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Opinion Mining ◽  
Disease Outbreaks ◽  
Semantic Networks ◽  
Web Crawler ◽  
Public Response ◽  
The Public

AbstractIt is necessary and important to understand public responses to crises, including disease outbreaks. Traditionally, surveys have played an essential role in collecting public opinion, while nowadays, with the increasing popularity of social media, mining social media data serves as another popular tool in opinion mining research. To understand the public response to COVID-19 on Weibo, this research collects 719,570 Weibo posts through a web crawler and analyzes the data with text mining techniques, including Latent Dirichlet Allocation (LDA) topic modeling and sentiment analysis. It is found that, in response to the COVID-19 outbreak, people learn about COVID-19, show their support for frontline warriors, encourage each other spiritually, and, in terms of taking preventive measures, express concerns about economic and life restoration, and so on. Analysis of sentiments and semantic networks further reveals that country media, as well as influential individuals and “self-media,” together contribute to the information spread of positive sentiment.

scholarly journals Speeding up calibration of latent Dirichlet allocation model to improve topic analysis in software engineering

2021 ◽  
Author(s):  
Jorge Arturo Lopez
Keyword(s):  
Software Engineering ◽  
Simple Formula ◽  
Latent Dirichlet Allocation ◽  
Allocation Model ◽  
Topic Analysis ◽  
Latent Dirichlet Allocation Model ◽  
Related Text ◽  
The Empirical Analysis ◽  
Large Corpus ◽  
Dirichlet Allocation

Extraction of topics from large text corpuses helps improve Software Engineering (SE) processes. Latent Dirichlet Allocation (LDA) represents one of the algorithmic tools to understand, search, exploit, and summarize a large corpus of data (documents), and it is often used to perform such analysis. However, calibration of the models is computationally expensive, especially if iterating over a large number of topics. Our goal is to create a simple formula allowing analysts to estimate the number of topics, so that the top X topics include the desired proportion of documents under study. We derived the formula from the empirical analysis of three SE-related text corpuses. We believe that practitioners can use our formula to expedite LDA analysis. The formula is also of interest to theoreticians, as it suggests that different SE text corpuses have similar underlying properties.

Long-term facilitation alters transmitter releasing properties at the crayfish neuromuscular junction

1986 ◽  
Vol 55 (3) ◽  
pp. 484-498 ◽  
Author(s):  
J. M. Wojtowicz ◽  
H. L. Atwood
Keyword(s):  
Neuromuscular Junction ◽  
Synaptic Transmission ◽  
Time Course ◽  
Muscle Fibers ◽  
Low Frequencies ◽  
Before And After ◽  
Binomial Parameter ◽  
Small Muscle ◽  
Long Term Facilitation

Synaptic transmission at the neuromuscular junction of the excitatory axon supplying the crayfish opener muscle was examined before and after induction of long-term facilitation (LTF) by a 10-min period of stimulation at 20 Hz. Induction of LTF led to a period of enhanced synaptic transmission, which often persisted for many hours. The enhancement was entirely presynaptic in origin, since quantal unit size and time course were not altered, and quantal content of transmission (m) was increased. LTF was not associated with any persistent changes in action potential or presynaptic membrane potential recorded in the terminal region of the excitatory axon. The small muscle fibers of the walking-leg opener muscle were almost isopotential, and all quantal events could be recorded with an intracellular microelectrode. In addition, at low frequencies of stimulation, m was small. Thus it was possible to apply a binomial model of transmitter release to events recorded from individual muscle fibers and to calculate values for n (number of responding units involved in transmission) and p (probability of transmission for the population of responding units) before and after LTF. In the majority of preparations analyzed (6/10), amplitude histograms of evoked synaptic potentials could be described by a binomial distribution with a small n and moderately high p. LTF produced a significant increase in n, while p was slightly reduced. The results can be explained by a model in which the binomial parameter n represents the number of active synapses and parameter p the mean probability of release at a synapse. Provided that a pool of initially inactive synapses exists, one can postulate that LTF involves recruitment of synapses to the active state.

scholarly journals Sentiment Analysis Methods for HPV Vaccines Related Tweets Based on Transfer Learning

Healthcare ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 307
Author(s):  
Li Zhang ◽  
Haimeng Fan ◽  
Chengxia Peng ◽  
Guozheng Rao ◽  
Qing Cong
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Hpv Vaccination ◽  
Experimental Results ◽  
Fine Tuning ◽  
Hpv Vaccines ◽  
Social Media Data ◽  
Public Sentiment ◽  
Media Data

The widespread use of social media provides a large amount of data for public sentiment analysis. Based on social media data, researchers can study public opinions on human papillomavirus (HPV) vaccines on social media using machine learning-based approaches that will help us understand the reasons behind the low vaccine coverage. However, social media data is usually unannotated, and data annotation is costly. The lack of an abundant annotated dataset limits the application of deep learning methods in effectively training models. To tackle this problem, we propose three transfer learning approaches to analyze the public sentiment on HPV vaccines on Twitter. One was transferring static embeddings and embeddings from language models (ELMo) and then processing by bidirectional gated recurrent unit with attention (BiGRU-Att), called DWE-BiGRU-Att. The others were fine-tuning pre-trained models with limited annotated data, called fine-tuning generative pre-training (GPT) and fine-tuning bidirectional encoder representations from transformers (BERT). The fine-tuned GPT model was built on the pre-trained generative pre-training (GPT) model. The fine-tuned BERT model was constructed with BERT model. The experimental results on the HPV dataset demonstrated the efficacy of the three methods in the sentiment analysis of the HPV vaccination task. The experimental results on the HPV dataset demonstrated the efficacy of the methods in the sentiment analysis of the HPV vaccination task. The fine-tuned BERT model outperforms all other methods. It can help to find strategies to improve vaccine uptake.

scholarly journals Crowd Event Perception Based on Spatiotemporal Weber Field

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Zhou Su ◽  
Hua Wei ◽  
Sha Wei
Keyword(s):  
Large Scale ◽  
Latent Dirichlet Allocation ◽  
Interaction Force ◽  
Motion Modeling ◽  
Allocation Model ◽  
Motion Patterns ◽  
Crowd Management ◽  
Latent Dirichlet Allocation Model ◽  
Spatiotemporal Signal ◽  
Crowd Motion

Over the past decade, a wide attention has been paid to the crowd control and management in intelligent video surveillance area. Among the tasks of automatic video-based crowd management, crowd motion modeling is recognized as one of the most critical components, since it lays a crucial foundation for numerous subsequent analyses. However, it still encounters many unsolved challenges due to occlusions among pedestrians, complicated motion patterns in crowded scenarios, and so forth. Addressing these issues, we propose a novel spatiotemporal Weber field, which integrates both appearance characteristics and stimulus of crowd motion patterns, to recognize the large-scale crowd event. On the one hand, crowd motion is recognized as variations of spatiotemporal signal, and we then measure the variation based on Weber law. The result is referred to as spatiotemporal Weber variation feature. On the other hand, motivated by the achievements in crowd dynamics that crowd motion has a close relationship with interaction force, we propose a spatiotemporal Weber force feature to exploit the stimulus of crowd behaviors. Finally, we utilize the latent Dirichlet allocation model to establish the relationship between crowd events and crowd motion patterns. Experiments on PETS2009 and UMN databases demonstrate that our proposed method outperforms the previous methods for the large-scale crowd behavior perception.

Engineering for Global Development: Characterizing the Discipline Through a Systematic Literature Review

2020 ◽  
Author(s):  
Grace Burleson ◽  
Jesse Austin-Breneman
Keyword(s):  
Literature Review ◽  
Systematic Literature Review ◽  
Mechanical Engineering ◽  
Latent Dirichlet Allocation ◽  
Descriptive Analysis ◽  
Secondary Data ◽  
Research Area ◽  
Global Development ◽  
Allocation Model ◽  
Latent Dirichlet Allocation Model

Abstract Over the past 50 years, researchers have repeatedly proposed the establishment of a new interdisciplinary engineering field in Engineering for Global Development (EGD), whose analytical tools and design processes result in positive social impacts and poverty alleviation in a global development context. Within each discipline and research area, a growing body of work has sought to systematically create scientific knowledge in this area. However, a recent network analysis of Human-Centered Design plus Development research indicates that sub-communities are not collaborating at a high level and therefore the overall research agenda may lack cohesion. This paper presents a descriptive analysis of EGD research within mechanical engineering along four dimensions through a systematic literature review and secondary data analysis. Results from the review and a Latent Dirichlet Allocation model indicate EGD work in mechanical engineering draws upon research methodologies from a number of other fields and has low levels of consensus on technical terminology. These results suggest consensus in the broader interdisciplinary EGD field should be examined.

Sign in / Sign up

Export Citation Format

Share Document