TY - GEN
T1 - Age Prediction of Social Media Users: Case Study on Robots in Hospitality
AU - Chen, Jinyuan
AU - Stantic, Bela
AU - Chen, Jinyan
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023/3
Y1 - 2023/3
N2 - Social media has gained popularity and we witness a vast volume of publicly available social media posts where people are commenting on different topics. This discussion contains a lot of valuable information deeply hidden inside the data and its metadata, which can be valuable for different stockholders. To extract this information different methods have been proposed in the literature and methods relied on different aspects of data and were based on diverse techniques such as text mining, machine and deep learning, predictive analytics, and natural language processing. This work proposes a method that relies on transformer-based architectures and it is based on supervised machine learning that predicts the age indirectly hidden in the description users provided in their profiles. To test the accuracy of the proposed method the case study of robots acceptance in hospitality has been considered. Relevant posts from social media Twitter have been collected and the proposed model tested. Results from extensive experimental evaluation demonstrate the suitability of the proposed method achieving high accuracy of age prediction, to the extent of 82% on test data. To demonstrate the usability and value of predicting the age of social media users we calculate the emotions as well as sentiment in posts and investigate the acceptance of robots in hospitality for different age groups.
AB - Social media has gained popularity and we witness a vast volume of publicly available social media posts where people are commenting on different topics. This discussion contains a lot of valuable information deeply hidden inside the data and its metadata, which can be valuable for different stockholders. To extract this information different methods have been proposed in the literature and methods relied on different aspects of data and were based on diverse techniques such as text mining, machine and deep learning, predictive analytics, and natural language processing. This work proposes a method that relies on transformer-based architectures and it is based on supervised machine learning that predicts the age indirectly hidden in the description users provided in their profiles. To test the accuracy of the proposed method the case study of robots acceptance in hospitality has been considered. Relevant posts from social media Twitter have been collected and the proposed model tested. Results from extensive experimental evaluation demonstrate the suitability of the proposed method achieving high accuracy of age prediction, to the extent of 82% on test data. To demonstrate the usability and value of predicting the age of social media users we calculate the emotions as well as sentiment in posts and investigate the acceptance of robots in hospitality for different age groups.
KW - Robotics and Hospitality
KW - Social media
KW - Supervised machine learning
KW - Transformer-based architectures
UR - http://www.scopus.com/inward/record.url?scp=85151053773&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-26889-2_39
DO - 10.1007/978-3-031-26889-2_39
M3 - Conference article published in proceeding or book
AN - SCOPUS:85151053773
SN - 9783031268885
T3 - Lecture Notes in Networks and Systems
SP - 426
EP - 437
BT - Robot Intelligence Technology and Applications 7 - Results from the 10th International Conference on Robot Intelligence Technology and Applications
A2 - Jo, Jun
A2 - Choi, Han-Lim
A2 - Helbig, Marde
A2 - Oh, Hyondong
A2 - Hwangbo, Jemin
A2 - Lee, Chang-Hun
A2 - Stantic, Bela
PB - Springer Science and Business Media Deutschland GmbH
T2 - 10th International Conference on Robot Intelligence Technology and Applications, RiTA 2022
Y2 - 7 December 2022 through 9 December 2022
ER -