An Exploratory Study of the Causes of Industrial Accidents Using Text Mining

2021 ◽  
Vol 9 (1) ◽  
pp. 1-11
Author(s):  
Hong-Kwan Kim ◽  
Yong-Woo Hwang ◽  
Young-Woo Chon ◽  
Jong-Uk Won ◽  
Chi-Nyon Kim ◽  
...  
Keyword(s):  
Text Mining ◽  
Exploratory Study ◽  
Industrial Accidents

Seeing is not always believing: an exploratory study of clickbait in WeChat

2020 ◽  
Vol 30 (3) ◽  
pp. 1043-1058
Author(s):  
Wenping Zhang ◽  
Wei Du ◽  
Yiyang Bian ◽  
Chih-Hung Peng ◽  
Qiqi Jiang
Keyword(s):  
Text Mining ◽  
Exploratory Study ◽  
Visual Rhetoric ◽  
Online Media ◽  
Content Type ◽  
Future Studies ◽  
Antecedents And Consequences ◽  
Rhetorical Features ◽  
Practical Implications ◽  
Different Levels

PurposeThe purpose of this study is to unpack the antecedents and consequences of clickbait prevalence in online media at two different levels, namely, (1) Headline-level: what characteristics of clickbait headlines attract user clicks and (2) Publisher-level: what happens to publishers who create clickbait on a prolonged basis.Design/methodology/approachTo test the proposed conjectures, the authors collected longitudinal data in collaboration with a leading company that operates more than 500 WeChat official accounts in China. This study proposed a text mining framework to extract and quantify clickbait rhetorical features (i.e. hyperbole, insinuation, puzzle, and visual rhetoric). Econometric analysis was employed for empirical validation.FindingsThe findings revealed that (1) hyperbole, insinuation, and visual rhetoric entice users to click the baited headlines, (2) there is an inverted U-shaped relationship between the number of clickbait headlines posted by a publisher and its visit traffic, and (3) this non-linear relationship is moderated by the publisher's age.Research limitations/implicationsThis research contributes to current literature on clickbait detection and clickbait consequences. Future studies can design more sophisticated methods for extracting rhetorical characteristics and implement in different languages.Practical implicationsThe findings could aid online media publishers to design attractive headlines and develop clickbait strategies to avoid user churn, and help managers enact appropriate regulations and policies to control clickbait prevalence.Originality/valueThe authors propose a novel text mining framework to quantify rhetoric embedded in clickbait. This study empirically investigates antecedents and consequences of clickbait prevalence through an exploratory study of WeChat in China.

scholarly journals Using text mining techniques to identify healthcare providers at risk: an exploratory study (Preprint)

2020 ◽  
Author(s):  
Iris Hendrickx ◽  
Tim Voets ◽  
Pieter van Dyk ◽  
Rudolph B Kool
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Text Mining ◽  
Sentiment Analysis ◽  
Exploratory Study ◽  
Healthcare Providers ◽  
Supervised Machine Learning ◽  
Care Providers ◽  
Severity Prediction ◽  
Dutch Health

BACKGROUND Regulatory bodies such as healthcare inspectorates can identify risks of healthcare providers by analyzing patient complaints. Text mining techniques (automatic text analysis based on machine learning), might help by identifying specific patterns and signals for risks on quality and safety issues. OBJECTIVE The aim of this study was to explore whether text mining techniques might be used to identify healthcare providers at risk. METHODS We performed an exploratory study on a complaints database of the Dutch Health and Youth Care Inspectorate with more than 22000 written complaints. We studied a range of supervised machine learning techniques to automatically determine the severity of incoming complaints. We investigated several features based on the complaints’ content, including sentiment analysis, to decide which were helpful for severity prediction. Finally, we took the list of health care providers and their organization-specific complaints to determine the average severity of complaints per organization. We performed a keyword analysis in order to give the Inspectorate insight in the patterns and severity per organization. RESULTS The data preparation and preprocessing were time-consuming one-off costs, mainly because we had to create a safe and efficient digital research environment. A straightforward text classification approach using a bag-of-words feature representation worked best for severity prediction. The usage of sentiment analysis for severity prediction was not helpful. Finally, we produced a list of n-grams of healthcare providers with the most complaints to inform the Inspectorate about the specific combination of words for these organizations. CONCLUSIONS Text mining techniques can support inspectorates with fully automatic analysis of complaints. They can give insights in patterns, detect possible blind spots, or support prioritizing follow-up supervision activities by sorting complaints on severity per organization or per sector. An appropriate data science and ICT infrastructure is crucial and indispensable for applied text mining.

Sign in / Sign up

Export Citation Format

Share Document