AnthroScore: A Computational Linguistic Measure of Anthropomorphism
- URL: http://arxiv.org/abs/2402.02056v1
- Date: Sat, 3 Feb 2024 06:36:11 GMT
- Title: AnthroScore: A Computational Linguistic Measure of Anthropomorphism
- Authors: Myra Cheng, Kristina Gligoric, Tiziano Piccardi, Dan Jurafsky
- Abstract summary: Anthropomorphism is the attribution of human-like characteristics to non-human entities.
We present AnthroScore, an automatic metric of implicit anthropomorphism in language.
- Score: 37.257294670068724
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Anthropomorphism, or the attribution of human-like characteristics to
non-human entities, has shaped conversations about the impacts and
possibilities of technology. We present AnthroScore, an automatic metric of
implicit anthropomorphism in language. We use a masked language model to
quantify how non-human entities are implicitly framed as human by the
surrounding context. We show that AnthroScore corresponds with human judgments
of anthropomorphism and dimensions of anthropomorphism described in social
science literature. Motivated by concerns of misleading anthropomorphism in
computer science discourse, we use AnthroScore to analyze 15 years of research
papers and downstream news articles. In research papers, we find that
anthropomorphism has steadily increased over time, and that papers related to
language models have the most anthropomorphism. Within ACL papers, temporal
increases in anthropomorphism are correlated with key neural advancements.
Building upon concerns of scientific misinformation in mass media, we identify
higher levels of anthropomorphism in news headlines compared to the research
papers they cite. Since AnthroScore is lexicon-free, it can be directly applied
to a wide range of text sources.
Related papers
- From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues [29.549159419088294]
Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions.
We show significant differences in these two types of responses and propose transitioning from one type to the other.
We introduce Pix2Persona, a novel dataset aimed at developing ethical and engaging AI systems in various embodiments.
arXiv Detail & Related papers (2024-10-04T19:06:24Z) - From "AI" to Probabilistic Automation: How Does Anthropomorphization of Technical Systems Descriptions Influence Trust? [10.608535718084926]
This paper investigates the influence of anthropomorphized descriptions of so-called "AI" (artificial intelligence) systems on people's self-assessment of trust in the system.
We find that participants are no more likely to trust anthropomorphized over de-anthropomorphized product descriptions overall.
arXiv Detail & Related papers (2024-04-08T17:01:09Z) - Inter-X: Towards Versatile Human-Human Interaction Analysis [100.254438708001]
We propose Inter-X, a dataset with accurate body movements and diverse interaction patterns.
The dataset includes 11K interaction sequences and more than 8.1M frames.
We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions.
arXiv Detail & Related papers (2023-12-26T13:36:05Z) - Agentivit\`a e telicit\`a in GilBERTo: implicazioni cognitive [77.71680953280436]
The goal of this study is to investigate whether a Transformer-based neural language model infers lexical semantics.
The semantic properties considered are telicity (also combined with definiteness) and agentivity.
arXiv Detail & Related papers (2023-07-06T10:52:22Z) - Anthropomorphization of AI: Opportunities and Risks [24.137106159123892]
Anthropomorphization is the tendency to attribute human-like traits to non-human entities.
With widespread adoption of AI systems, the tendency for users to anthropomorphize it increases significantly.
We study the objective legal implications, as analyzed through the lens of the recent blueprint of AI bill of rights.
arXiv Detail & Related papers (2023-05-24T06:39:45Z) - A Targeted Assessment of Incremental Processing in Neural LanguageModels
and Humans [2.7624021966289605]
We present a scaled-up comparison of incremental processing in humans and neural language models.
Data comes from a novel online experimental paradigm called the Interpolated Maze task.
We find that both humans and language models show increased processing difficulty in ungrammatical sentence regions.
arXiv Detail & Related papers (2021-06-06T20:04:39Z) - Cetacean Translation Initiative: a roadmap to deciphering the
communication of sperm whales [97.41394631426678]
Recent research showed the promise of machine learning tools for analyzing acoustic communication in nonhuman species.
We outline the key elements required for the collection and processing of massive bioacoustic data of sperm whales.
The technological capabilities developed are likely to yield cross-applications and advancements in broader communities investigating non-human communication and animal behavioral research.
arXiv Detail & Related papers (2021-04-17T18:39:22Z) - Mechanisms for Handling Nested Dependencies in Neural-Network Language
Models and Humans [75.15855405318855]
We studied whether a modern artificial neural network trained with "deep learning" methods mimics a central aspect of human sentence processing.
Although the network was solely trained to predict the next word in a large corpus, analysis showed the emergence of specialized units that successfully handled local and long-distance syntactic agreement.
We tested the model's predictions in a behavioral experiment where humans detected violations in number agreement in sentences with systematic variations in the singular/plural status of multiple nouns.
arXiv Detail & Related papers (2020-06-19T12:00:05Z) - A Framework for the Computational Linguistic Analysis of Dehumanization [52.735780962665814]
We analyze discussions of LGBTQ people in the New York Times from 1986 to 2015.
We find increasingly humanizing descriptions of LGBTQ people over time.
The ability to analyze dehumanizing language at a large scale has implications for automatically detecting and understanding media bias as well as abusive language online.
arXiv Detail & Related papers (2020-03-06T03:02:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.