1,720,979 research outputs found
Code for Decision-Making Algorithm Twitter Data NLP Analysis
No full textCode for tweet extraction, topic modelling, sentiment analysis and emotion detection
ChatGPT Twitter Data - NLP Analysis
No full textTopic modelling, sentiment analysis and emotion detection results from NLP analysis of tweets relating to ChatGPT
NHS Covid-19 App Twitter Data - NLP Analysis
No full textTopic modelling, sentiment analysis and emotion detection results from the analysis of tweets relating to the NHS Covid-19 contact-tracing app
A Level Algorithm Twitter Data - NLP Analysis
No full textTopic modelling, sentiment analysis and emotion detection results for Twitter data associated with the 2020 A Level grade calculation algorithm. All tweets are in the form of tweet IDs
APOLLO: an open platform for LLM-based multi-agent interaction research
No full textTraditional decision-making processes often struggle to capture diverse stakeholder perspectives and anticipate potential outcomes. Complex decisions and persuasions might rely on insights and perspectives which might not be available. In this paper, we leverage recent advances in large language models and retrieval-augmented generation to introduce APOLLO—an Architecture and oPen-source system that Orchestrates Large Language mOdels. APOLLO coordinates multiple LLMs by engaging them in collaborative discourse to reach a consensus on user-defined prompts. This system enables HCI and AI researchers and practitioners, and allows them to explore and experiment with LLM-based multi-agents systems in a user-configurable and customisable manner. By providing this flexible platform, APOLLO enables new avenues for studying and designing human-AI interactions, investigating the impact of multi-agent interaction on human behaviour, and ultimately facilitates a deeper understanding of how AI-driven collaboration can enhance human-AI interaction and decision making.</p
A survey of lay people’s willingness to generate legal advice using Large Language Models (LLMs)
No full textAs of November 2022-following the release of OpenAI's ChatGPT-the general public's awareness of generative AI, and specifically Large Language Models (LLMs) has increased. LLMs such as ChatGPT now have the capability to generate text indistinguishable from human authored text, which comes with numerous risks. In this paper, we investigate public perception and willingness to use LLMs as a substitute for legal advice from legal professionals. Our findings show that while few people have used it for this purpose, the willingness to rely on LLMs in the future is growing. Interestingly, this depends on the specific area of law, and while LLMs are perceived to be highly valuable in relation to topics such as tenancy and tax law, they seem to be perceived as less valuable in contexts such as divorce or civil disputes.</p
Objection overruled! Lay people can distinguish large language models from lawyers, but still favour advice from an LLM
No full textLarge Language Models (LLMs) are seemingly infiltrating every domain, and the legal context is no exception. In this paper, we present the results of three experiments (total N=288) that investigated lay people's willingness to act upon, and their ability to discriminate between, LLM- and lawyer-generated legal advice. In Experiment 1, participants judged their willingness to act on legal advice when the source of the advice was either known or unknown. When the advice source was unknown, participants indicated that they were significantly more willing to act on the LLM-generated advice. This result was replicated in Experiment 2. Intriguingly, despite participants indicating higher willingness to act on LLM-generated advice in Experiments 1 and 2, participants discriminated between the LLM- and lawyer-generated texts significantly above chance-level in Experiment 3. Lastly, we discuss potential explanations and risks of our findings, limitations and future work, and the importance of language complexity and real-world comparability
Privacy Preserving Corpus Linguistics: Investigating the Trajectories of Public Health Messaging Online
Full text linkThe Coronavirus Discourses project supports public health partners Public Health Wales, Public Health England, and NHS Education for Scotland in addressing key challenges that the coronavirus pandemic presents in terms of understanding the flow and impact of public health messages in public and private communications.In this report, we outline a set of guiding principles for privacy- preserving research for researchers and professionals, which applies to a new approach we have developed, mainly relating to the development of PriPA (Privacy Preserving Analytics).Next, we introduce the PriPA (Privacy Preserving Analytics) Extension. The PriPA extension is a digital tool designed for anyone to use on their personal devices. It safely retrieves information about individual language use for analysis. The advantage of this browser extension is that users have full control over what information they want to share
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
