Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 26 for “"LDA topic modeling"”.
-
Zum Verständnis des LDA Topic Modeling: eine Evaluation aus Sicht der Digital Humanities
Als quantitative Textanalysemethode ist das LDA Topic Modeling in den letzten Jahren in den Digital Humanities weit verbreitet worden, um zahlreiche unstrukturierte Textdaten zu untersuchen. Wenn man LDA Topic Modeling anwendet, muss man mit vielen Faktoren umgehen, die das Ergebnis der …
-
Mining e-scooter safety policies and plans with GPT-4o and Latent Dirichlet Allocation (LDA) topic modeling
… text analysis and Latent Dirichlet Allocation (LDA) topic modeling for statistical extraction of high-frequency e-scooter safety planning topics. The findings reveal significant gaps and inconsistencies in e-scooter safety regulations, emphasizing the need for enhanced focus on roadway …
-
Studying the Evolution of Bitcoin-Related Topics Extracted from an Online Forum
… over the past 10 years. We found 31 different topics in the forum by applying LDA topic modeling and categorized them into 6 categories: Future, General, Mining, Monetary, Regulations, and Technical. Our investigation on this work finds a relation between Bitcoin price and the sentiment …
-
Understand omnichannel customer value and the human-machine user experience when using mobile application
… methods, including textual data pre-processing, LDA topic modeling, sentimental analysis, word co-occurrence network. This is the first attempt to quantify fashion retailing data using text-mining methods to thoroughly investigate the user/consumer experience in omnichannel shopping. Based on the …
-
Topic Modeling and Culturomic Analysis of 30,000 Books Over 100 Years Using Gensim
… Project Gutenberg, Latent Dirichlet Allocation (LDA) topic modeling was applied to identify recurring themes across eleven decades. The study sought to determine whether historically significant events could be detected within fictional narratives. One clear instance emerged: Napoleon Bonaparte …
-
Understanding the Relationship between Online Discussions and Bitcoin Return and Volume: Topic Modeling and Sentiment Analysis
… period. Using Latent Dirichlet Allocation (LDA) topic modeling algorithm, we discover eight distinct topics: Mining, Regulation, Investment/trading, Public perception, Bitcoin’s nature, Wallet, Payment, and Other. Importantly, we find differences in relations between different topics’ …
-
Decoding Relations between Geopolitical Risk and Financial Markets
… tensions. Using Latent Dirichlet Allocation (LDA) topic modeling, it identifies key topics discussed in business media. Through ordinary least squares and quantile regression analyses, the thesis examines the relationship between topic sentiment (polarity) and hype (intensity), and financial …
-
Exploring the Agenda-Setting Dynamics Between Traditional Newspapers and Twitter During Mass Shooting Event
… incidents. Applying Latent Dirichlet Allocation (LDA) topic modeling to data sourced from Twitter, national, and local news, the study investigated the distinct coverage patterns and the extent of their reciprocal influence over time. The findings of this study demonstrated that, in the immediate …
-
Analyzing Twitter Sentiment and Hype on Real Estate Market: A Topic Modeling Approach
… 2010 to 2021. Using Latent Dirichlet Allocation (LDA) topic modeling algorithm, we identify seven unique topics related to the housing market based on people's tweets: Households, Economic policy, Commercial real estate, Price and rate, Residential housing, Investing, and Future trends. We gather …
-
Dynamics of polarized discourse : gender antagonism on Twitter in the 2022 South Korean election
… that integrates Latent Dirichlet Allocation (LDA) topic modeling with qualitative close reading, the research analyzes a corpus of 6,000 tweets across three distinct temporal phases: pre-election, election week, and post-election. The findings reveal the process of constructing Gender …
-
Analyzing Motorcycle Crashes on Rural Undivided Roads: A Data-Driven Approach
… on injury severity. Latent Dirichlet Allocation (LDA) topic modeling of crash narratives further supplements the analysis by uncovering key crash scenarios and thematic trends. The results consistently show that excessive speed, loss of control, helmet non-use, and hazardous roadway geometry, such …
-
Towards better management of organizational cybersecurity
… historical cyber incidents. In addition, we use LDA topic modeling on disclosed annual risk reports from organizations (Form 10-K Item 1A) to extract topic features. By leveraging these data, our model effectively predicts future security incidents.
-
Evolution of Blockchain Technology: Dynamics of Knowledge Flow and Thematic Trends
… by incorporating various methodologies such as LDA topic modeling, citation network analysis, and main path analysis. The categorization of blockchain technology into topics was conducted using the LDA machine learning model, which can provide more objective and robust topic classification than …
-
Text Mining Contemporary Popular Fiction: Natural Language Processing-Derived Themes Across Over 1,000 New York Times Bestsellers and Genre Fiction Novels
… of popular fictional material, to see what topics emerge when viewed across genre lines and from a new, “machine” perspective. The dataset consists of 1,136 popular and commercially successful novels published between 2005 and 2016, including New York Times bestsellers and “genre fiction,” …
-
Anthropomorphism and Audience Engagement: Unlocking the Potential of Virtual Influencers
… adopted an ethnography methodology by utilizing LDA topic modeling to analyze audience engagement themes with virtual influencers, pinpointing parasocial relationships, physical attractiveness, hedonic value, and expertise. In the subsequent section, I established a framework linking …
-
Understanding ELL Stack Exchange: An Investigation into Discussion Topics and Answer Acceptance Criteria
… Utilizing Latent Dirichlet Allocation (LDA) topic modeling, the study analyzed 27,847 questions from 2013, 2017, and 2021. The analysis identified seven key topics of discussions among which, Topic 6 (Grammar and Meaning) with 1,372 questions in 2013, 4,514 questions in 2017, and 4,232 …
-
Ekphrastic Revisions: Verbal-Visual Networks in 20th Century Poetry by Women
… which establishes best practices for using LDA topic modeling and social network analysis to read the ekphrastic genre at scale using a curated dataset of more than 4700 poems. In using tools available to the digital humanities, I take into consideration the range of possible questions that …
-
Link formation in mobile and economic networks : model and empirical analysis
… businesses using latent Dirichlet allocation (LDA) topic modeling, and constructs a novel business proximity measure based on the output. Using CrunchBase data including 24,382 high-tech companies and 1,689 M&A transactions, we empirically validate our business proximity measure in the context …
-
Characterizing Health Behavior Information: Developing A Surveillance Text Mining Framework Using Twitter For Diet, Diabetes, Exercise, And Obesity
… exercise, and obesity to characterize the topics associated with them; a human evaluation of the sentiment analysis and topic results was also conducted. The research questions guiding this study are: RQ1: What are the positive and negative sentiments of Twitter users regarding diet, …
-
Modelling Topic and Sentiment Evolution in Twitter Based on Word Embedding for Classification of Trends in Different Domains
… the web. To help with this challenge, we utilize LDA topic modeling to identify the dynamic of sentiment evolution over time. We also examine one domain’s sentiment influence over other domains by investigating the close relationship of opinion in social networks. In addition, traditional news …
Page 1 of 2