The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.

Though only 23 minutes on the high-speed rail from Shenzhen North to West Kowloon, the journey from the mainland to Hong Kong seems to transport me back half a century. The concrete jungle of my childhood memories hasn't changed one bit. Time seems trapped in the amber of this city of seven million, while the Shenzhen Bay area that I departed has already arrived at the future ahead of schedule. My classmate from a decade earlier, Dr. Ng Lok Tin of the Hong Kong University of Science and Technology, waits for me at the station exit. As though to highlight the discombobulation of modern China, he greets me in Cantonese though he's a native of Shanghai; I, Hong Kong born, on the other hand, speak to him in Modern Standard Mandarin. "Leung Wah Kiu, what's this really about?" he asks me. "A few days ago, two plainclothes officers approached me to ask if Professor Lau had been in touch and for the contact info of his relatives and friends in Hong Kong." "I thought he had been placed in ...

A common problem for companies with strong business growth is that it is hard to find enough experienced staff to support expansion needs. This problem is particular pronounced for operations planners and controllers who must be very highly knowledgeable and experienced with the business domain. This article is a case study of how one of the largest travel agencies in Hong Kong alleviated this problem by using AI to support decision-making and problem-solving so that their planners and controllers can work more effectively and efficiently to sustain business growth while maintaining consistent quality of service. AI is used in a mission critical fleet management system (FMS) that supports the scheduling and management of a fleet of luxury limousines for business travelers. The AI problem was modeled as a constraint satisfaction problem (CSP). The use of AI enabled the travel agency to sign up additional hotel partners, handle more orders and expand their fleet with their existing team of planners and controllers. Using modern web 2.0 architecture and proven AI technology, we were able to achieve low-risk implementation and deployment success with concrete and measurable business benefits.