Hsuan Lei Shao

Dr. Hsuan Lei Shao

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 February 2023 in Frontiers in Psychology
Verified
Journal Article
Open access
CZChang Zhang
Chang Zhang
DZDechun Zhang
Dechun Zhang
HSHsuan Lei Shao
Hsuan Lei Shao
Introduction: Social media infuses modern relationships with vitality and brings a series of information dissemination with subjective consciousness. Studies have indicated that official Chinese media channels are transforming their communication style from didactic hard persuasion to softened emotional management in the digital era. However, previous studies have rarely provided valid empirical evidence for the communicational transformation. The study fills the gap by providing a longitudinal time-series analysis to reveal the pattern of communication of Chinese digital Chinese official media from 2019 to 2022.Method: The study crawler collected 43,259 posts from the People’s Daily’s Weibo account from 2019 to 2021. The study analyzed the textual data with using trained artificial intelligence models.Results: This study explored the practices of the People’s Daily’s Weibo account from 2019 to 2021, COVID-19 is hardly normalized as it is still used as the justification for extraordinary measures in China. This study confirmed that People’s Daily’s Weibo account posts are undergoing softenization transformation, with the use of soft news, positive energy promotion, and the embedding of sentiment. Although the outburst of COVID-19 temporarily increased the media’s use of hard news, it only occur at the initial stage of the pandemic. Emotional posts occupy a nonnegligible amount of the People’s Daily Weibo content. However, the majority of posts are emotionally neutral and contribute to shaping the authoritative image of the party press.Discussion: Overall, the People’s Daily has softened their communication style on digital platforms and used emotional mobilization, distraction, and timely information provision to balance the political logic of building an authoritative media agency and the media logic of constructing audience relevance.

29 June 2021
Verified
Book Chapter
Closed access
PDF file
HSHsuan Lei Shao
Hsuan Lei Shao
YCYi-Chia Chen
Yi-Chia Chen
SHSieh-Chuen Huang
Sieh-Chuen Huang

2 December 2025
Verified
Book Chapter
Open access
YYYing-Chu Yu
Ying-Chu Yu
SHSieh-Chuen Huang
Sieh-Chuen Huang
HSHsuan Lei Shao
Hsuan Lei Shao
This paper presents a multi-agent AI framework for legal aid, designed to support real-world case fact management through interactive dialogue. Our agent framework emulates the iterative questioning, clarification, and synthesis processes of legal professionals, not solely on the fragmented information initially provided by litigants. By engaging in multi-turn interactions, the system incrementally supplements missing details and mitigates risks of misinterpretation, thereby aligning more closely with the dynamics of real legal consultations. A key contribution of this work is the use of real-world legal aid case records as training and evaluation material, ensuring that the framework is grounded in authentic data rather than synthetic simulations. The system is implemented as a collaboration among specialized agents: (1) litigantTwins, which maintains factual integrity and guards against hallucinations; (2) legalAider, which leverages legal knowledge to generate context-sensitive follow-up questions and update case narratives; and (3) Evaluator, which compares AI-generated case records against ground truth facts, assessing factual correctness through qualitative and quantitative measures. Technically, the framework can be built on LLMs, with multi-agent system and prompt design enabling robust coordination. This architecture enhances the quality of fact construction and reasoning, while also offering a scalable solution for online public legal aid services. Beyond its technical contributions, this research highlights its public value, accessibility, and commitment to fairness in the distribution of legal resources. By integrating multi-agent AI with real-world case data, the framework addresses both the technological and socio-legal dimensions of legal information systems, advancing on legal knowledge management, deployment of conversational agents, and normative reasoning in multi-agent systems.

1 January 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
HSHsuan Lei Shao
Hsuan Lei Shao
Xi Jinping’s attitude have become the core indicator for observing the CCP's situation, and his ideology have also been an important dynamic in China politics. This study attempts to answer: "The characteristics of Xi Jinping's ideological system and its temporal changes", especially the relationship with Maoism. The method of this research is "Computational Politics/Computational China Studies", which uses computers as the core to explore the parts that are difficult to find by human beings. Specifically, the texts of speeches in the "Xi Jinping Series Important Speech Database", over ten thousand samples were collected as analysis corpus. We use programming techniques such as text mining, natural language processing, and deep learning algorithms to build analytical models and perform extensive annotation. This research specifically achieves an automated machine to process a large amount of corpus, and implements its batch process analysis; secondly, it uses natural language processing to extract its discourse features, which tries to model its ideological system. The above techniques are used to examine Xi Jinping's ten-year term (2012-2021) using words and ideological changes. The study found that Xi's ideology indeed has a trend of upward spiral like Maoism, and the reference to post-Maoism is relatively stable, but the tendency to struggle has gradually increased since the "Sino-US trade war", which proves the trend of wolf-diplomacy

15 June 2022 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
SHSieh-Chuen Huang
Sieh-Chuen Huang
HSHsuan Lei Shao
Hsuan Lei Shao
RLRobert B Leflar
Robert B Leflar
The doctrine of ‘best interests of the child’ has guided courts in determining post-divorce child custody cases in Taiwan since 1996 amendments to the Civil Code. Amended Article 1055-1 requires judges to consider factors such as ‘the age, sex, and wishes of the child’ and ‘the age, occupation, character, health condition, economic condition, and lifestyle of the parents.’ However, previous studies have not clarified which factors judges consider primary. This Article collects Taiwanese family court decisions from 2012 to 2017, involving 1,126 children whose parents were both Taiwanese and who both sought to acquire custody, in which Taiwanese district courts granted sole custody to the husband or wife. The Article employs decision tree methodology, a commonly used machine learning technology. The Article concludes that the three most significant factors considered by Taiwanese judges are first, which parent is the child’s current primary caregiver, followed by the wishes of the child and the judge’s assessment of parent-child interaction. This result runs counter to widely held beliefs that parental gender and parents’ occupations and economic resources are still prime factors in judges’ contemplation. Decision tree learning, we suggest, can assist parents’ and lawyers’ case evaluations and speed extrajudicial custody determination arrangements.