Pseudo-document simulation for comparing LDA, GSDMM and GPM topic models on short and sparse text using Twitter data

Weisser, Christoph; Gerloff, Christoph; Thielmann, Anton; Python, André; Reuter, Arik; Kneib, Thomas; Säfken, Benjamin

doi:10.1007/s00180-022-01246-z

Cited by 26 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also has a precise method for balancing the completeness and homogeneity of the clustering results. It can also obtain the representative words of each cluster (Weisser et al , 2022).…”

Section: Methodsmentioning

confidence: 99%

Decoding mood of the Twitterverse on ESG investing: opinion mining and key themes using machine learning

Jaiswal,

Gupta,

Tiwari

2024

MRR

View full text Add to dashboard Cite

Purpose Grounded in the stakeholder theory and signaling theory, this study aims to broaden the research agenda on environmental, social and governance (ESG) investing by uncovering public sentiments and key themes using Twitter data spanning from 2009 to 2022. Design/methodology/approach Using various machine learning models for text tonality analysis and topic modeling, this research scrutinizes 1,842,985 Twitter texts to extract prevalent ESG investing trends and gauge their sentiment. Findings Gibbs Sampling Dirichlet Multinomial Mixture emerges as the optimal topic modeling method, unveiling significant topics such as “Physical risk of climate change,” “Employee Health, Safety and well-being” and “Water management and Scarcity.” RoBERTa, an attention-based model, outperforms other machine learning models in sentiment analysis, revealing a predominantly positive shift in public sentiment toward ESG investing over the past five years. Research limitations/implications This study establishes a framework for sentiment analysis and topic modeling on alternative data, offering a foundation for future research. Prospective studies can enhance insights by incorporating data from additional social media platforms like LinkedIn and Facebook. Practical implications Leveraging unstructured data on ESG from platforms like Twitter provides a novel avenue to capture company-related information, supplementing traditional self-reported sustainability disclosures. This approach opens new possibilities for understanding a company’s ESG standing. Social implications By shedding light on public perceptions of ESG investing, this research uncovers influential factors that often elude traditional corporate reporting. The findings empower both investors and the general public, aiding managers in refining ESG and management strategies. Originality/value This study marks a groundbreaking contribution to scholarly exploration, to the best of the authors’ knowledge, by being the first to analyze unstructured Twitter data in the context of ESG investing, offering unique insights and advancing the understanding of this emerging field.

show abstract

“…It also has a precise method for balancing the completeness and homogeneity of the clustering results. It can also obtain the representative words of each cluster (Weisser et al , 2022).…”

Section: Methodsmentioning

confidence: 99%

Decoding mood of the Twitterverse on ESG investing: opinion mining and key themes using machine learning

Jaiswal,

Gupta,

Tiwari

2024

MRR

View full text Add to dashboard Cite

show abstract

“…The researcher [4] explores the challenge of applying topic models to the brief and sparse texts commonly found in social media micro-blogs, such as Twitter. A comparison of three models is carried out, which include the standard Latent Dirichlet Allocation (LDA), the Gibbs Sampler Dirichlet Multinomial Model (GSDMM), and the Gamma Poisson Mixture Model (GPM), the latter two being specifically tailored for sparse data.…”

Section: Literature Reviewmentioning

confidence: 99%

Sentiment Analysis and Topic Classification with LSTM Networks and TextRazor

Jency Jose,

Simritha R

2024

International Journal of Data Informatics and Intelligent Compu

View full text Add to dashboard Cite

In the ever-evolving landscape of social media, where user-generated content shapes digital discourse, the need for nuanced sentiment analysis and topic extraction is paramount. This paper presents a comprehensive approach utilizing advanced Natural Language Processing (NLP) techniques to enhance user experience and foster a healthier digital environment. Leveraging Long Short-Term Memory (LSTM) networks for sentiment analysis and TextRazor for topic extraction, the system provides insights into emotional tones and key themes within social media discussions. Through intuitive visualizations, users gain awareness of sentiment trends and topic distributions, empowering informed engagement. The results demonstrate high accuracy in sentiment classification with 86% and effective topic identification, contributing to the mitigation of misinformation and negativity online. This research underscores the potential of advanced NLP methods in cultivating constructive digital spaces and sets the stage for further innovation in the field.

show abstract

“…Comparing GSDMM and LDA, the GSDMM is better suited to short texts as it assumes that there is one topic in the text [9,10].…”

Section: Brief Justification For Choosing Gsdmm For Text Clustering I...mentioning

confidence: 99%

Explore actual sustainable energy topics by using Yake!, Krovetz, GSDMM and short text summaries

Chigarev¹

2023

Preprint

View full text Add to dashboard Cite

This paper considers the reasonability of using GSDMM as a method for clustering short texts - titles and abstracts of publications 2021-2023 of MDPI journals on sustainable energy topics. The paper proposes an approach to identifying relevant research topics based on the use of the Python script Yake!, the Krovetz streamer, the GSDMM algorithm, and short text annotations. It is emphasized that researchers prefer to rely on specific publications rather than keywords when searching for information on a topic of interest. The bibliometric records of sustainable energy publications from 2021 to 2023 in Sustainability (Energy Sustainability section — 1,926 search results) and Energies (Sustainable Energy section — 994 search results) were used as data for analysis. The GSDMM algorithm was used to cluster the texts, and Yake! to extract the keywords for the GSDMM algorithm's vocabulary. This article summarizes topics found in 9 clusters, including general sustainable energy issues, biomass recycling, region-specific issues, building energy use, economic growth and investment, numerical flow modeling, generation cost optimization, heat to energy conversion, weather-related risks, and false data attacks.

show abstract

Pseudo-document simulation for comparing LDA, GSDMM and GPM topic models on short and sparse text using Twitter data

Cited by 26 publications

References 18 publications

Decoding mood of the Twitterverse on ESG investing: opinion mining and key themes using machine learning

Decoding mood of the Twitterverse on ESG investing: opinion mining and key themes using machine learning

Sentiment Analysis and Topic Classification with LSTM Networks and TextRazor

Explore actual sustainable energy topics by using Yake!, Krovetz, GSDMM and short text summaries

Contact Info

Product

Resources

About