Twitter Data Mining for the Social Awareness of Emerging Technologies

Li, Xin; Xie, Qianqian; Huang, Lucheng; Zhou, Yuan

doi:10.23919/picmet.2017.8125279

Cited by 9 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, to the best of our knowledge, no consistent and systematic evaluation protocol for trend forecasting methods has been developed. For example, some studies evaluated using trended entities alone without considering the ability to distinguish between trending and non-trending entities (Li et al 2017). Other studies focused on evaluating the classification performance of trending status while ignoring the prediction of periods corresponding to those trends (Bandari, Asur, and Huberman 2012;Yu, Asur, and Huberman 2015).…”

Section: Introductionmentioning

confidence: 99%

Construction of Evaluation Datasets for Trend Forecasting Studies

Matsuno

Mizuki

Sakaki

2023

ICWSM

View full text Add to dashboard Cite

In this study, we discuss issues in the traditional evaluation norms of trend forecasts, outline a suitable evaluation method, propose an evaluation dataset construction procedure, and publish Trend Dataset: the dataset we have created. As trend predictions often yield economic benefits, trend forecasting studies have been widely conducted. However, a consistent and systematic evaluation protocol has yet to be adopted. We consider that the desired evaluation method would address the performance of predicting which entity will trend, when a trend occurs, and how much it will trend based on a reliable indicator of the general public's recognition as a gold standard. Accordingly, we propose a dataset construction method that includes annotations for trending status (trending or non-trending), degree of trending (how well it is recognized), and the trend period corresponding to a surge in recognition rate. The proposed method uses questionnaire-based recognition rates interpolated using Internet search volume, enabling trend period annotation on a weekly timescale. The main novelty is that we survey when the respondents recognize the entities that are highly likely to have trended and those that haven't. This procedure enables a balanced collection of both trending and non-trending entities. We constructed the dataset and verified its quality. We confirmed that the interests of entities estimated using Wikipedia information enables the efficient collection of trending entities a priori. We also confirmed that the Internet search volume agrees with public recognition rate among trending entities.

show abstract

Section: Introductionmentioning

confidence: 99%

Construction of Evaluation Datasets for Trend Forecasting Studies

Matsuno

Mizuki

Sakaki

2023

ICWSM

View full text Add to dashboard Cite

show abstract

“…Using these techniques to follow the newest technological advancements aids the improvement of business operations. The most common data sources tech mining is applied to include patents [2,3], scientific publications [4,5], and recently, social media data [6,7] and website data [8].…”

Section: Introductionmentioning

confidence: 99%

Human Resources Mining for Examination of R&D Progress and Requirements

Ozcan

Şakar

Suloglu

2021

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

The amount of job advertisement data is rapidly growing, and this rich dataset is expected to have implications for the employment market, sector trajectories and the education sector. Most significantly, human resources (HR) data has never previously been examined with the lens of tech mining for science and technology analyses. Our study is the first to examine job advertisement data considering research and development (R&D) progress and requirements, and hereafter we refer to this as HR mining. The aim of this study is to use HR mining with the purpose of R&D and human capital intelligence using the job advertisement data of Turkey for the 2015-2017 period. The method of this study follows classification as part of the pre-processing step to determine R&D, engineering and high-tech industry-related job advertisements. Afterwards, we use clustering methods to identify areas where key human capital is required, and investments are made by R&D-oriented companies. The results show that it is possible to identify sector-oriented skill requirements and that the significance of the R&D skills varies. For the case of Turkey, we can clearly show the national human capital and R&D by identifying nine key clusters that indicate R&D progress and directions.

show abstract

“…Matching the document with a lexicon of awareness expression markers [9]; • Extracting co-occurring or frequently occurring keywords from the document [4,10] Based on the previous explanation, sentiment analysis is the most commonly applied technique. The implementation of sentiment analysis is limited to how people's opinions are linked to their level of awareness, without knowing what topics people have or have yet to understand.…”

mentioning

confidence: 99%

Exploring Community Awareness of Mangrove Ecosystem Preservation through Sentence-BERT and K-Means Clustering

Kusumaningrum,

Khoerunnisa,

Khadijah

et al. 2024

Information

View full text Add to dashboard Cite

The mangrove ecosystem is crucial for addressing climate change and supporting marine life. To preserve this ecosystem, understanding community awareness is essential. While latent Dirichlet allocation (LDA) is commonly used for this, it has drawbacks such as high resource requirements and an inability to capture semantic nuances. We propose a technique using Sentence-BERT and K-Means Clustering for topic identification, addressing these drawbacks. Analyzing mangrove-related Twitter data in Indonesian from 1 September 2021 to 31 August 2022 revealed nine topics. The visualized tweet frequency indicates a growing public awareness of the mangrove ecosystem, showcasing collaborative efforts between the government and society. Our method proves effective and can be extended to other domains.

show abstract

Twitter Data Mining for the Social Awareness of Emerging Technologies

Cited by 9 publications

References 19 publications

Construction of Evaluation Datasets for Trend Forecasting Studies

Construction of Evaluation Datasets for Trend Forecasting Studies

Human Resources Mining for Examination of R&D Progress and Requirements

Exploring Community Awareness of Mangrove Ecosystem Preservation through Sentence-BERT and K-Means Clustering

Contact Info

Product

Resources

About