Improved Text Classification of Long-term Care Materials

1044

Authors

nan

Abstract

AbstractAging populations have posed a challenge to many countries including Taiwan, and with them come the issue of long-term care. Given the current context, the aim of this study was to explore the hotly-discussed subtopics in the field of long-term care, and identify its features through NLP. This study applied TF-IDF, the Logistic Regression model, and the Naive Bayes classifier to process data. In sum, the results showed that it reached a best F1-score of 0.920 in identification, and a best accuracy of 0.708 in classification. The results of this study could be used as a reference for future long-term care related applications.

Keywords

nan

Full Content

Abstract Aging populations have posed a challenge to many countries including Taiwan, and with them come the issue of long-term care. Given the current context, the aim of this study was to explore the hotly-discussed subtopics in the field of long-term care, and identify its features through NLP. Texts from forums and websites were utilized for data collection and analysis. The study applied TF-IDF, the logistic regression model, and the naive Bayes classifier to process data. In sum, the results showed that it reached a F1-score of 0.92 in identification, and a best accuracy of 0.71 in classification. Results of the study found that apart from TF-IDF features, certain words could be elicited as favorable features in classification. The results of this study could be used as a reference for future long-term care related applications. Keywords: long-term care, natural language processing (NLP), text classification, Chinese Improved Text Classification of Long-term Care Materials ��� Yi Fan Chiang ������������ Graduate Institute of Linguistics National Chengchi University vianne6@gmail.com ��� Chi-Ling Lee ������������������ Master’s & Doctor’s Program in Teaching Chinese as a Second Language National Chengchi University 19940818jillian@gmail.com ��� Heng-Chia Liao ����������������� Master’s Program in Teaching Chinese as a Second Language National Chengchi University 106161011@nccu.edu.tw ��� Yi-Ting Tsai ������������ Graduate Institute of Linguistics National Chengchi University 109555005@nccu.edu.tw ��� Yu-Yun Chang ������������ Graduate Institute of Linguistics National Chengchi University yuyun@nccu.edu.tw The 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021) Taoyuan, Taiwan, October 15-16, 2021. The Association for Computational Linguistics and Chinese Language Processing 294 1 Introduction Long-term care, by the definition of Ministry of Health and Welfare1, refers to “the living support, assistance, social participation, care and relevant healthcare services in accordance with the needs of any individual whose mental or physical incapacity has lasted or is expected to last for six months or longer”. As for long-term care services, according to Harris-Kojetin et al. (2019), include assistance with activities of daily living (abbreviated as ADLs, which includes activities such as dressing, bathing, and toileting), instrumental activities of daily living (abbreviated as IADLs, which includes activities such as medication management and housework), and health maintenance tasks. Long- term care services assist people to improve or maintain an optimal level of physical functioning and quality of life, which can include help from other people and special equipment or assistive devices. According to National Development Council (2020)2, driven by a low birth rate of 1.2 and an all- time high life expectancy in 2020, senior citizens (people aged 65 or older) will account for over 20 percent of Taiwan's total population by 2025, indicating Taiwan will step into a super-aged society. Within the context, how long-term care services can meet the escalating demand is absolutely critical. While extensive long-term care studies have been conducted, few of them are from the perspective of caregivers, especially family caregivers. Chen (2013) pointed out that long-term care system in Taiwan lacked support services for the caregivers. For most family caregivers, they provided ADLs and IADLs for their family members. …

Content truncated to 500 words

Labeled Text

AbstractAging populations have posed a challenge to many countries including Taiwan, and with them come the issue of long-term care. Given the current context, the aim of this study was to explore the hotly-discussed subtopics in the field of long-term care, and identify its features through NLP. This study applied TF-IDF, the Logistic Regression model, and the Naive Bayes classifier to process data. In sum, the results showed that it reached a best F1-score of 0.920 in identification, and a best accuracy of 0.708 in classification. The results of this study could be used as a reference for future long-term care related applications.

Publication Details

Paper ID:
1044
Year:
2021
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan