Applying GIS and Text Mining Methods to Twitter Data to Explore the Spatiotemporal Patterns of Topics of Interest in Kuwait

Almatar, Muhammad G; Alazmi, Huda S.; Li, Liuqing; Fox, Edward A.

doi:10.3390/ijgi9120702

Cited by 9 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we did not investigate whether there is a statistical difference between GUs with high and low number of geotagged tweets. Future work could address these limitations by utilizing methods to infer demographic information such as the gender of users (e.g., analyzing the name of users), analyzing non-English tweets, studying other types of location Twitter sharing strategies, such as place-tagging, investigating differences regarding different times and locations, exploring categories of GUs based on the number of geotagged tweets, and analyzing special and temporal factors such as spatiotemporal analysis of tweets [74]. It would also be interesting to expand this study by comparing users based on their county (e.g., GUs vs. NGUs in Canada or France).…”

Section: Discussionmentioning

confidence: 99%

Analysis of Geotagging Behavior: Do Geotagged Users Represent the Twitter Population?

Karami

Kadari

Panati

et al. 2021

IJGI

View full text Add to dashboard Cite

Twitter’s APIs are now the main data source for social media researchers. A large number of studies have utilized Twitter data for diverse research interests. Twitter users can share their precise real-time location, and Twitter APIs can provide this information as longitude and latitude. These geotagged Twitter data can help to study human activities and movements for different applications. Compared to the mostly small-scale data samples in different domains, such as social science, collecting geotagged data offers large samples. There is a fundamental question whether geotagged users can represent non-geotagged users. While some studies have investigated the question from different perspectives, they did not investigate profile information and the contents of tweets of geotagged and non-geotagged users. This empirical study addresses this limitation by applying text mining, statistical analysis, and machine learning techniques on Twitter data comprising more than 88,000 users and over 170 million tweets. Our findings show that there is a significant difference (p-value < 0.001) between geotagged and non-geotagged users based on 73% of the features obtained from the users’ profiles and tweets. The features can also help to distinguish between geotagged and non-geotagged users with around 80% accuracy. This research illustrates that geotagged users do not represent the Twitter population.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of Geotagging Behavior: Do Geotagged Users Represent the Twitter Population?

Karami

Kadari

Panati

et al. 2021

IJGI

View full text Add to dashboard Cite

show abstract

“…Some researchers have also applied bibliometric theories to track topics and influencing factors in research fields by analyzing high-frequency keywords and specialized terms [19][20][21]. Furthermore, some researchers utilize web crawlers to obtain word frequency data from online forums and analyze the most frequent words to capture the main issues discussed in those forums [22][23][24]. This method can quickly reveal the evolution of topics in a specific discipline.…”

Section: Literature Review 21 Development and Academic Application Of...mentioning

confidence: 99%

How Could Consumers’ Online Review Help Improve Product Design Strategy?

Miao

Lin

et al. 2023

Information

View full text Add to dashboard Cite

This study aims to explore the utilization of user-generated content for product improvement and decision-making processes. In the era of big data, the channels through which enterprises obtain user feedback information are transitioning from traditional methods to online platforms. The original data for this study were obtained from customer reviews of cordless hairdryers on JD.com. The specific process is as follows: First, we used the Python Requests package to crawl 20,157 initial comments. Subsequently, the initial data were cleaned, resulting in 1405 valid comments. Next, the cleaned and valid comments were segmented into Chinese words using the HanLP package. Finally, the Latent Dirichlet Allocation (LDA) method was applied for topic modeling. The visualization of the topic clustering was generated using pyLDAvis, and three optimal topics were identified. These topics were named “User Experience”, “Product Evaluation”, and “Product Features”, respectively. Through data analysis and expert consultation, this study developed product design improvement strategies based on online reviews and verified the validity of the developed cordless hairdryer design index system through a questionnaire survey, providing practical references and innovative theoretical foundations for future product design assessments.

show abstract

“…We have found that there is a gap in the field of natural language processing for the Kuwaiti dialect; there is limited availability of linguistic resources for this dialect, with only a few published research papers in the field of NLP focusing on it [14][15][16][17].…”

Section: Natural Language Processing (Nlp) Of Kuwaiti Dialectmentioning

confidence: 99%

Q8VaxStance: Dataset Labeling System for Stance Detection Towards Vaccines in Kuwaiti Dialect

Alostad,

Dawiek,

Davulcu

2023

Preprint

View full text Add to dashboard Cite

The Kuwaiti dialect is a particular dialect of Arabic spoken in Kuwait; it differs significantly from standard Arabic and the dialects of neighboring countries in the same region. Few research papers with a focus on the Kuwaiti dialect have been published in the field of NLP. In this study, we created Kuwaiti dialect language resources using Q8VaxStance, a vaccine stance labeling system for a large dataset of tweets. This dataset will fill this gap and provide a valuable resource for researchers studying vaccine hesitancy in Kuwait. Furthermore, it will contribute to the Arabic natural language processing field by providing a dataset for developing and evaluating machine learning models for stance detection in the Kuwaiti dialect. The proposed vaccine stance labeling system combines the benefits of weak supervised learning and zero-shot learning; for this purpose, we implemented 52 experiments on 42815 unlabeled tweets extracted between December 2020 and July 2022. The results of the experiments show that using keyword detection in conjunction with zero-shot model labeling functions is significantly better than using only keyword detection labeling functions or just zero-shot model labeling functions. Furthermore, using the Arabic language in both the labels and prompt or a mix of Arabic labels and an English prompt is statistically significant compared to using English in both the labels and prompt for the total number of generated labels evaluation metric. Finally, the best accuracy for Macro-F1 values were found in the experiments KHZSLF-EE4 and KHZSLF-EA1, with values of 0.83 and 0.83, respectively. And, for the total automatically labeled data evaluation metric, experiment KHZSLF-EE4 labeled 42,270 tweets, while experiment KHZSLF-EA1 was able to generate 42,764 labels.

show abstract

Applying GIS and Text Mining Methods to Twitter Data to Explore the Spatiotemporal Patterns of Topics of Interest in Kuwait

Cited by 9 publications

References 37 publications

Analysis of Geotagging Behavior: Do Geotagged Users Represent the Twitter Population?

Analysis of Geotagging Behavior: Do Geotagged Users Represent the Twitter Population?

How Could Consumers’ Online Review Help Improve Product Design Strategy?

Q8VaxStance: Dataset Labeling System for Stance Detection Towards Vaccines in Kuwaiti Dialect

Contact Info

Product

Resources

About