Study on an Argumentation-Based Negotiation in Human-Computer Negotiation Service

Cao, Mukun; Gong, Jing

doi:10.1007/978-3-030-30967-1_23

Cited by 1 publication

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Afterward, we corrected or removed all the flags to ensure the reliability and correctness of the annotation. The communication units were marked as two different categories by two annotators as shown in table 5. 1.…”

Section: Buyer Responsementioning

confidence: 99%

“…Therefore, there is a need for more intelligent system support to handle this huge concurrent trading volume. However, the prevalent B2C e-commerce sites currently in use (such as Jingdong & Tmall) mostly rely on fixed-price transactions [5]. Thereby, customers must use instant messaging services (like Ali Want) to haggle with their customer service staff in order to negotiate the price with sellers.…”

Section: Introductionmentioning

confidence: 99%

“…However, JIMI and AliMe cannot handle the requests from clients for price reductions or services like shipping, warranty, refund policy, etc. Therefore, customers must approach back-office customer support representatives to negotiate on price reductions, which is not a true automation [5]. There is a need of such conversational agents that cannot only comprehend the human language but can also identify the intent (Purchase or non-Purchase) at content level and engaged humans (buyers) in a bilateral business negotiation to achieve more deals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Primitive-based Learning Model for Intent Detection in Human-AI Agent Negotiation

Waseem,

Shoaib,

Arshad

2023

Preprint

View full text Add to dashboard Cite

Intent detection task is one of the core problems in the natural language understanding (NLU) as it enables the conversational agents to comprehend the human language for meaningful interaction. But human-AI agent communication is not fully rational due to the dynamic behaviour of the human. Several research works have been carried out to ascertain intent detection methods for social media (Twitter, Facebook) chat, email conversation, and product reviews etc. However, we cannot deploy existing intent detection methods in a real-time human-AI agent negotiation scenario. In this article, we present the first primitive-based learning model, which analyses human (buyer) dynamic behavioral patterns at content level, and automatically predict their purchase or non-purchase intent during a bilateral business negotiation. Thereby, by evaluating and keeping track of two key human behaviors “affective” & “disappointment”, an AI agent can therefore, better comprehend the human intent and engage them in the negotiation, and achieve more agreements (deals). We employ negotiation primitives by setting them to pertinent (human-human) communication units for enhancing the cognition and decision-making capability of AI-agents and evaluate its performance on various machine learning models including BERT. With 93% accuracy, the proposed model itself has proven to be a more efficient method for classifying e-negotiation behavioral patterns.

show abstract

Section: Buyer Responsementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation