Overview and analysis of the text mining applications in the construction industry

Yan, Hang; Ma, Mingxue; Wu, Ying; Fan, Hongqin; Dong, Chao

doi:10.1016/j.heliyon.2022.e12088

Cited by 10 publications

(4 citation statements)

References 129 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data obtained from UGC are gathered by content analysis conducted for consumers' brand associations. But manual analysis of UGC datasets is a difficult process due to the size of the data and its unstructured nature (Elsayed et al, 2019;Yan et al, 2022).…”

Section: Approaches Using User-generated Contentmentioning

confidence: 99%

Assessing Destination Brand Associations on Twitter: The case of Istanbul

KASAPOĞLU

Aksoy

Başkol

2023

Advances in Hospitality and Tourism Research (AHTR)

View full text Add to dashboard Cite

The development of data mining has paved the way for studies that identify brand associations from user-generated content (UGC). However, the number of studies investigating destination associations with social media is limited. The aim of this study is to explore destination associations with UGC on Twitter and to show how data mining and sentiment analysis methods can be applied to destinations to elicit brand associations. In this study, 33,339 English-language tweets containing the word #Istanbul were collected over one year and analyzed using text mining (association rule analysis) and sentiment analysis. As a result of the study, a brand concept map (BCM) of what Twitter users associate with Istanbul was created and compared to other studies that measure associations using conventional methods. The main results show that users have positive associations with tourism in Istanbul. Unique and interesting associations (such as "cats") were observed compared to other previous studies that measured associations to destinations. Based on the study results, a method was proposed for measuring the image of a place brand by observing electronic word of mouth in social media.

show abstract

Section: Approaches Using User-generated Contentmentioning

confidence: 99%

Assessing Destination Brand Associations on Twitter: The case of Istanbul

KASAPOĞLU

Aksoy

Başkol

2023

Advances in Hospitality and Tourism Research (AHTR)

View full text Add to dashboard Cite

show abstract

“…These reports provide valuable information, as they not only describe the sequence of events leading to an accident but also provide a comprehensive analysis of its causes [14]. Accident reports may be extensive and contain large amounts of textual data, making it difficult to effectively extract relevant and meaningful insights [15]. In addition, information may be structured in different ways or use different terminology, further complicating the extraction process [3].…”

Section: Introductionmentioning

confidence: 99%

Integrating Information Entropy and Latent Dirichlet Allocation Models for Analysis of Safety Accidents in the Construction Industry

et al. 2023

View full text Add to dashboard Cite

Construction accident investigation reports contain critical information, but extracting useful insights from the voluminous Chinese text is challenging. Traditional methods rely on expert judgment, which leads to time-consuming and potentially inaccurate results. To overcome this problem, we propose a novel approach that combines text mining techniques and latent Dirichlet allocation (LDA) models to analyze standardized accident investigation reports in the Chinese construction industry. The proposed method integrates an information entropy term frequency-inverse document frequency (TF-IDF) weighting scheme to evaluate term importance and accounts for word and model uncertainty. The method was applied to a set of construction industry accident reports to identify the key factors leading to safety accidents. The results show that the causal factors of accidents in Chinese accident investigation reports consist of keywords and negative expressions, including “failure to timely identify safety hazards” and “inadequate site safety management”. Failure to timely identify safety hazards is the most common factor in accident investigation reports, and the negative expressions commonly used in the reports include “not timely” and “not in place”. The information entropy TF-IDF method is superior to traditional methods in terms of accuracy and efficiency, and the LDA model that considers word frequency and feature weights is better able to capture the underlying themes in the Chinese corpus. And the subject terms that make up the themes contain more information about the causes of accidents. This approach helps site managers more quickly and effectively understand the causal factors and key messages that lead to accidents from incident reports. It gives site managers insight into common patterns and themes associated with safety incidents, such as unsafe practices, hazardous work environments, and non-compliance with safety regulations. This enables them to make informed decisions to improve safety management practices.

show abstract

“…Therefore, many studies have developed sentiment analysis techniques from twitter or other datasets to be able to generalize and even predict from the processed sentiment data [6], [7]. Text mining is a machine learning method that aims to gather information and obtain high accuracy in classifying predictions on a class of data [8], [9]. Sentiment analysis is part of data mining, various optimizations with various algorithms are carried out in order to achieve high accuracy performance [10].…”

Section: Introductionmentioning

confidence: 99%

Global recession sentiment analysis utilizing VADER and ensemble learning method with word embedding

Ningsih,

Wibowo,

Dullah

et al. 2023

J. Soft Comput. Explor.

View full text Add to dashboard Cite

The issue of the Global Recession is hitting various countries, including Indonesia. Many Indonesians have expressed their opinions on the issue of the global recession in 2023, one of which is from Twitter. By understanding public sentiment, we can assess the impact felt by the public on the issue itself. Sentiment analysis in this research is a form of support to evaluate Indonesia's sustainability in dealing with the issue of Global Recession in accordance with the Sustainable Development Goals (SDGs). However, in previous research, it is still rare to find a model that has good performance in conducting Global Recession Sentiment Analysis. Therefore, the purpose of this research is to propose a machine learning model that is expected to provide good performance in sentiment analysis. The existing sentiment dataset is labeled with the Valence Aware Dictionary for Social Reasoning (VADER) algorithm, then an Ensemble Learning method is designed which is composed of Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM) algorithms. After that, the Countvectorizer feature extraction with N-Gram, Best Match 25 (BM25), and Word Embedding is carried out to convert sentences in the dataset into numerical vectors so as to improve model performance. The research results provide a more optimal accuracy performance of 95.02% in classifying sentiment. So that the proposed model successfully performs sentiment analysis better than previous research.

show abstract

Overview and analysis of the text mining applications in the construction industry

Cited by 10 publications

References 129 publications

Assessing Destination Brand Associations on Twitter: The case of Istanbul

Assessing Destination Brand Associations on Twitter: The case of Istanbul

Integrating Information Entropy and Latent Dirichlet Allocation Models for Analysis of Safety Accidents in the Construction Industry

Global recession sentiment analysis utilizing VADER and ensemble learning method with word embedding

Contact Info

Product

Resources

About