Natural language processing versus rule-based text analysis: Comparing BERT score and readability indices to predict crowdfunding outcomes

Chan, C.S. Richard; Pethe, Charuta; Skiena, Steven

doi:10.1016/j.jbvi.2021.e00276

Cited by 12 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our analysis, we controlled for Preciseness (negative of the type-token ratio, implemented using korPus package in R), Concreteness (the sum of the number of articles, prepositions, and quantifiers); Interactivity (the number of question marks); PsychologicalDistancing (the number of first-person pronouns – “I,” “we,” and “you” – as a proportion of the total number of words); and Readability (the average length of a sentence in number of words). Readability was also used as a control variable, as it positively affects the audience’s (reader’s) motivation to fund the campaign (Chan et al , 2021).…”

Section: Methodsmentioning

confidence: 99%

Putting your money where your mouth is – the role of rewards in a value-based understanding of restaurant crowdfunding

Kedas

Sarkar

2022

IJCHM

View full text Add to dashboard Cite

Purpose Restaurant entrepreneurs are increasingly leveraging crowdfunding as an alternative financing mechanism. In the context of restaurant crowdfunding, studies have identified factors related to campaign communication that affect crowdfunding success from the entrepreneurs’ perspective. Integrating a funder perspective, this study aims to investigate the role of the consumption value offered by rewards and builds a value-based understanding of restaurant crowdfunding. Design/methodology/approach This study uses a sample of 3,134 restaurant campaigns launched on the Kickstarter crowdfunding platform, and texts of 34,128 rewards were analyzed using a Python program. A hierarchical linear regression approach with a generalized logistic regression model was adopted to test hypothesized relationships. Findings Drawing upon consumption value theory (CVT), this study finds that in restaurant crowdfunding, utilitarian value holds a strong inverted-U relationship and participatory value holds a strong linear relationship with crowdfunding success. However, socioemotional value does not have a significant effect on outcomes. This study also finds evidence for positive effects of greater variety, higher number of rewards and lower average pledge level on restaurant crowdfunding success. Practical implications This study extends the literature on restaurant crowdfunding by integrating insights on the effects of value offered through rewards. Primarily, this study finds evidence for distinct effects of consumption values for restaurant crowdfunding audience. Practically, this study holds implications for reward menu design and value offering design for restaurant entrepreneurs seeking crowdfunding. Originality/value Restaurant crowdfunding has been studied to a limited extent, with extant literature focusing on characteristics of campaign descriptions. The role of rewards is uncovered using CVT and thus a value-based understanding of restaurant crowdfunding is presented.

show abstract

Section: Methodsmentioning

confidence: 99%

Putting your money where your mouth is – the role of rewards in a value-based understanding of restaurant crowdfunding

Kedas

Sarkar

2022

IJCHM

View full text Add to dashboard Cite

show abstract

“…The BERTScore is easy to use and resolves several limitations of commonly used metrics [42]. The Precision score is calculated by matching each token in the candidate set to each token in the reference set.…”

Section: Evaluating Labelsmentioning

confidence: 99%

Automatic label curation from large-scale text corpus

Avasthi,

Chauhan

2024

Eng. Res. Express

View full text Add to dashboard Cite

The topic modeling technique extracts themes based on their probabilistic measurements from any large-scale text collection. Even though topic modeling pulls out the most important phrases that describe latent themes in text collections, a suitable label has yet to be found. Interpreting the topics extracted from a text corpus and identifying a suitable label automatically reduces the cognitive load for the analyst. Extractive methods are used typically to select a label from a given candidate set, based on probability metrics for each candidate set. Some of the existing approaches use phrases, words, and images to generate labels using frequency counts of different words in the text. The paper proposes a method to generate labels automatically to represent each topic based on a labeling strategy to filter candidate labels and then apply sequence-to-sequence labelers. The objective of the method is to get a meaningful label for the result of the Latent Dirichlet Allocation algorithm. The BERTScore metric is used to evaluate the effectiveness of the proposed method. The proposed method generates good interpretative labels as compared to baseline models for topic words or terms automatically. The comparison with the label generated through ChatGPT API shows the quality of the generated label with the experiment performed on Four Datasets NIPS, Kindle, PUBMED, and CORD-19.

show abstract

“…They learn contextualised text representations by predicting words based on their context utilising a huge amount of text data. Using artificial intelligence to process, arrange, and extract embedded information from texts, or natural language processing (NLP), a branch of linguistics and computer science [89]. Any statement that disparages an individual or a group on the basis of a trait such as race, colour, ethnicity, gender, sexual orientation, nationality, religion, or another characteristic is usually referred to as hate speech [90].…”

Section: The Use Of Natural Language Processing To Forecast Visual De...mentioning

confidence: 99%

Semantic Context and Attention-driven Framework for Predicting Visual Description Utilizing a Deep Neural Network and Natural Language Processing

Shetty

Bhat

2023

IJCSBE

View full text Add to dashboard Cite

Background/Purpose: This literature review's goal is to inspect various machine learning algorithms for visual description and their applications to prediction. Examining the numerous approaches mentioned in this area brings up a fresh avenue for expanding the current research methods. Design/Methodology/Approach: The study results that are provided in different scholarly works are acquired from secondary sources, such as scholarly journal publications. This review study analyses these articles and highlights their interpretations. Findings/Result: This research focuses on several cataloguing methods for isolated identifying images and visions. When developing research topics in the idea of inaccessible detecting geographic information systems, the gaps discovered during analysis using various methodologies have made things simpler. Research limitations/implications: This study examined a range of AI tool uses. The scope of this work is rivetted to a assessment of the many machine-learning implementation strategies for analysis and prediction. More research might be done on the many deep learning constructions for image and video classification. Originality/Value: The articles chosen for this study's review are from academic journals and are cited by other authors in their works. The articles that were selected for the examination have a connection to the investigation and research plan described in the paper. Paper Type: Literature review paper.

show abstract

Natural language processing versus rule-based text analysis: Comparing BERT score and readability indices to predict crowdfunding outcomes

Cited by 12 publications

References 30 publications

Putting your money where your mouth is – the role of rewards in a value-based understanding of restaurant crowdfunding

Putting your money where your mouth is – the role of rewards in a value-based understanding of restaurant crowdfunding

Automatic label curation from large-scale text corpus

Semantic Context and Attention-driven Framework for Predicting Visual Description Utilizing a Deep Neural Network and Natural Language Processing

Contact Info

Product

Resources

About