Use of offensive language in human-artificial intelligence chatbot interaction: The effects of ethical ideology, social competence, and perceived humanlikeness

Park, Namkee; Jang, Kyungeun; Cho, Seonggyeol; Choi, Jin-Young

doi:10.1016/j.chb.2021.106795

Cited by 37 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…e goodwill value evaluation of the cultural industry based on wavelet neural networks in this paper can not only reflect the characteristics of wavelet neural network that effectively extract the local information of signals, have selflearning, adaptability and fault tolerance, high precision and fast convergence speed, and avoids the blindness of BP neural networks and other structural designs but also evaluate the goodwill value of the cultural industry from the perspective of combining qualitative and quantitative analysis from a unique perspective [9]. e hierarchical structure of the wavelet neural network is more suitable for the hierarchical stratification and classification of the factors affecting the goodwill value of the cultural industry, so as to more effectively and accurately build an evaluation index system and determine the value of the cultural industry in terms of goodwill according to the evaluation index.…”

Section: Analysis Of Constituent Elementsmentioning

confidence: 99%

Scientific Research Management Helping the Development of Regional Cultural Industry from the Perspective of Artificial Intelligence

Wang

2022

Mobile Information Systems

View full text Add to dashboard Cite

In order to solve the problem that traditional scientific research management is restricted by management methods and tools, and it is difficult to realize the development of cultural industry, this paper proposes a research method that scientific research management helps the development of the regional cultural industry from the perspective of artificial intelligence. Based on a wavelet neural network based on artificial intelligence, this paper establishes the goodwill value evaluation of cultural industry development under scientific research management. Firstly, the paper uses the hierarchical structure theory to construct the theoretical analysis framework and evaluation index system of cultural value and divides the influencing factors of cultural industry value into three levels: input layer network structure, hidden layer network structure, and output layer network structure. Then the wavelet neural network method is used to analyze, and the three-layer network structure is superimposed to reflect the hierarchical relationship between the index systems. Through the combination of normative analysis and empirical analysis, it verifies that the method has unique advantages and feasibility and realizes the promotion of scientific research management to the development of the regional cultural industry.

show abstract

Section: Analysis Of Constituent Elementsmentioning

confidence: 99%

Scientific Research Management Helping the Development of Regional Cultural Industry from the Perspective of Artificial Intelligence

Wang

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Further, continued deployment of such a system, with appropriate learning systems, could then potentially keep improving over time (Carlson et al, 2010;Agichtein et al, 2006;Madotto et al, 2021;Shuster et al, 2021b), where (Hancock et al, 2019) refer to this approach as a self-feeding chatbot. The challenge, however, is that organic users may not be invested enough to want to provide adequate feedback, and some may be adversarial (Park et al, 2021) as in the case of Microsoft's Tay (Davis, 2016).…”

Section: Related Workmentioning

confidence: 99%

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

Shuster¹,

Xu²,

Komeili³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a longterm memory, and having been trained on a large number of user defined tasks. We release both the model weights and code, and have also deployed the model on a public web page to interact with organic users. This technical report describes how the model was built (architecture, model and training scheme), and details of its deployment, including safety mechanisms. Human evaluations show its superiority to existing open-domain dialogue agents, including its predecessors Komeili et al., 2022). Finally, we detail our plan for continual learning using the data collected from deployment, which will also be publicly released. The goal of this research program is thus to enable the community to study ever-improving responsible agents that learn through interaction. * * We use the phrase continual learning in the sense of learning that continues over time using data from the model's interactions, but training itself will actually be performed in successive large batches; the model is not updated online.† Equal contribution.

show abstract

“…Recurrent neural network (RNN) units cannot memorize values for long periods [12]. To solve the gradient vanishing problem in RNNs, researchers have proposed gated recursive units (GRU) and long short-term memory (LSTM), respectively, to replace hidden layer neurons with memory units that store early sequence data [31].…”

Section: Encoding Layermentioning

confidence: 99%

“…However, the online learning technology of chatbots, which allows them to learn and develop as they interact with users, constantly enriches the diversity of the response corpus while also making them subject to some influences related to the user's language use in the learning process [11]. A hacker or offensive user can use the online learning interface of a chatbot to teach extreme semantics to the robot, resulting in an improper semantics by the chatbot, violating local laws and regulations [12,13]. For example, only a few hours after Tay is online, offensive users exploit its training vulnerability to teach Tay racist semantics (including racial discrimination, gender discrimination, propaganda of violence, white supremacy, and genocide), resulting in the offline of the product.…”

Section: Introductionmentioning

confidence: 99%

A Reinforcement Learning-based Offensive semantics Censorship System for Chatbots

Cai¹,

Han²,

Zheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

The rapid development of artificial intelligence (AI) technology has enabled large-scale AI applications to land in the market and practice. However, while AI technology has brought many conveniences to people in the productization process, it has also exposed many security issues. Especially, attacks against online learning vulnerabilities of chatbots occur frequently. Therefore, this paper proposes a semantics censorship chatbot system based on reinforcement learning, which is mainly composed of two parts: the Offensive semantics censorship model and the semantics purification model. Offensive semantics review can combine the context of user input sentences to detect the rapid evolution of Offensive semantics and respond to Offensive semantics responses. The semantics purification model For the case of chatting robot models, it has been contaminated by large numbers of offensive semantics, by strengthening the offensive reply learned by the learning algorithm, rather than rolling back to the early versions. In addition, by integrating a once-through learning approach, the speed of semantics purification

show abstract

Use of offensive language in human-artificial intelligence chatbot interaction: The effects of ethical ideology, social competence, and perceived humanlikeness

Cited by 37 publications

References 31 publications

Scientific Research Management Helping the Development of Regional Cultural Industry from the Perspective of Artificial Intelligence

Scientific Research Management Helping the Development of Regional Cultural Industry from the Perspective of Artificial Intelligence

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

A Reinforcement Learning-based Offensive semantics Censorship System for Chatbots

Contact Info

Product

Resources

About