Understanding Customers’ Transport Services with Topic Clustering and Sentiment Analysis

Moreno, Alejandro; Iglesias, Carlos Á.

doi:10.3390/app112110169

Cited by 6 publications

(5 citation statements)

References 28 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Long COVID syndrome was first described as a set of fuzzy symptoms that persisted following COVID-19 recovery using patient-created vocabulary. According to the SA performed by the authors [49], opinions about the long COVID syndrome can be equally split between positive (19.90%) and negative (18.39%). Similarly, the study performed by [33] emphasizes how the Indian government's progressive unlocks and lockdowns of various areas during the Corona outburst were perceived by the general population.…”

Section: B the Relevant Sectors Of Activity Where The Clustering Algo...mentioning

confidence: 99%

Clustering Algorithms in Sentiment Analysis Techniques in Social Media – A Rapid Literature Review

Pavaloaia

2024

IJACSA

View full text Add to dashboard Cite

Based on the high dynamic of Sentiment Analysis (SA) topic among the latest publication landscape, the current review attempts to fill a research gap. Consequently, the paper elaborates on the most recent body of literature to extract and analyze the papers that elaborate on the clustering algorithms applied on social media datasets for performing SA. The current rapid review attempts to answer the research questions by analyzing a pool of 46 articles published in between Dec 2020 -Dec 2023. The manuscripts were thoroughly selected from Scopus (Sco) and WebOf-Science (WoS) databases and, after filtering the initial pool of 164 articles, the final results (46) were extracted and read in full.

show abstract

Section: B the Relevant Sectors Of Activity Where The Clustering Algo...mentioning

confidence: 99%

Clustering Algorithms in Sentiment Analysis Techniques in Social Media – A Rapid Literature Review

Pavaloaia

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…We updated the value of the ith node in layer l, as shown in Equation (3). The final output of the GCN is shown in Equation (4).…”

Section: Graph Convolutional Network Layermentioning

confidence: 99%

“…In this way, the statement is partially understood. This is currently an important tool for online opinion gathering for governments and businesses concerning policies or business strategies [4]. For example, it can be used to analyze a company's blockchain statements and obtain a short-term value evaluation of the company [5].…”

Section: Introductionmentioning

confidence: 99%

A Graph Convolutional Network Based on Sentiment Support for Aspect-Level Sentiment Analysis

Gao,

Jiang,

Zou

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Aspect-level sentiment analysis is a research focal point for natural language comprehension. An attention mechanism is a very important approach for aspect-level sentiment analysis, but it only fuses sentences from a semantic perspective and ignores grammatical information in the sentences. Graph convolutional networks (GCNs) are a better method for processing syntactic information; however, they still face problems in effectively combining semantic and syntactic information. This paper presents a sentiment-supported graph convolutional network (SSGCN). This SSGCN first obtains the semantic information of the text through aspect-aware attention and self-attention; then, a grammar mask matrix and a GCN are applied to preliminarily combine semantic information with grammatical information. Afterward, the processing of these information features is divided into three steps. To begin with, features related to the semantics and grammatical features of aspect words are extracted. The second step obtains the enhanced features of the semantic and grammatical information through sentiment support words. Finally, it concatenates the two features, thus enhancing the effectiveness of the attention mechanism formed from the combination of semantic and grammatical information. The experimental results show that compared with benchmark models, the SSGCN had an improved accuracy of 6.33–0.5%. In macro F1 evaluation, its improvement range was 11.68–0.5%.

show abstract

“…Therefore, the data is divided into 7 groups (all tweets, USA user tweets, India user tweets, male user tweets, female user tweets, younger user tweets, and older user tweets). Then, 14 documents, which include 7 groups, pre-, and amid-pandemic from 2019.01 to 2022.05, are used for topic modeling based on the LDA model (5 clusters based) (66). Finally, 35 clusters, each cluster has 20 keywords, are collected.…”

Section: Abstract Extractionmentioning

confidence: 99%

An analysis of ridesharing trip time pre- and amid-COVID-19 pandemic using advanced text mining technique – the USA vs Indian case study across different age and gender groups

Sobhani²,

et al. 2023

Preprint

View full text Add to dashboard Cite

With the spread of the Covid-19 virus, the public transportation industry faced new challenges. This disease may have affected the decision of users in choosing travel modes by diluting the strengths of ridesharing. In this study, our aim was to investigate the opinions of users on the Twitter application pre- and post-pandemic about travel time in ridesharing. For this purpose, we analyzed 63,800 tweets from January 1, 2019 to April 30, 2022, focusing on the countries of the United States and India, taking into account the characteristics of users such as age and gender. The method we used was LDA for topic modelling and BERT for sentiment analysis. Our results show that trip time happening, such as mornings and other times, became more important after COVID-19 and users' concern about waiting time has increased. After the pandemic, men are more worried about the waiting time, while women and younger groups are worried about the time cost. Before the pandemic, older people gave more importance to waiting time, but after the pandemic, they are more concerned about the time cost and the trip time happening. We also found that women and US users were more positive than others about ridesharing trip time in the pre-pandemic era. Our findings showed that two main factors, the pandemic and the country, greatly affect sentiment, and the positive sentiment of the users of both countries increased after the epidemic, which was higher among all groups for the elderly and American users. Our results can be used to analyze the sentiments of ridesharing industry users in order to compete with other public transportation companies by providing better services and designing a standard to improve travel time.

show abstract

Understanding Customers’ Transport Services with Topic Clustering and Sentiment Analysis

Cited by 6 publications

References 28 publications

Clustering Algorithms in Sentiment Analysis Techniques in Social Media – A Rapid Literature Review

Clustering Algorithms in Sentiment Analysis Techniques in Social Media – A Rapid Literature Review

A Graph Convolutional Network Based on Sentiment Support for Aspect-Level Sentiment Analysis

An analysis of ridesharing trip time pre- and amid-COVID-19 pandemic using advanced text mining technique – the USA vs Indian case study across different age and gender groups

Contact Info

Product

Resources

About