paper-with-me

Papers

Detecting Egregious Conversations between Customers and Virtual Agents

2017-11-15 · NAACL 2018 6 · Tommy Sandbank, Michal Shmueli-Scheuer, Jonathan Herzig, David Konopnicki, John Richards, David Piorkowski

Virtual agents are becoming a prominent channel of interaction in customer service. Not all customer interactions are smooth, however, and some can become almost comically bad. In such instances, a human agent might need to step in and salvage the conversation. Detecting bad conversations is important since disappointing customer service may threaten customer loyalty and impact revenue. In this paper, we outline an approach to detecting such egregious conversations, using behavioral cues from the user, patterns in agent responses, and user-agent interaction. Using logs of two commercial systems, we show that using these features improves the detection F1-score by around 20% over using textual features alone. In addition, we show that those features are common across two quite different domains and, arguably, universal.

📄 PDF Abstract BibTeX arXiv:1711.05780

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Detecting Speech Act Types in Developer Question/Answer Conversations During Bug Repair

2018-06-13 · Andrew Wood, Paige Rodeghero, Ameer Armaly, Collin McMillan

This paper targets the problem of speech act detection in conversations about bug repair. We conduct a "Wizard of Oz" experiment with 30 professional programmers, in which the programmers fix bugs for two hours, and use …

Detecting egregious responses in neural sequence-to-sequence models

2018-09-11 · ICLR 2019 5 · Tianxing He, James Glass

In this work, we attempt to answer a critical question: whether there exists some input sequence that will cause a well-trained discrete-space neural network sequence-to-sequence (seq2seq) model to generate egregious out…

Response Generation

Don't get Lost in Negation: An Effective Negation Handled Dialogue Acts Prediction Algorithm for Twitter Customer Service Conversations

2018-07-16 · Mansurul Bhuiyan, Amita Misra, Saurabh Tripathy, Jalal Mahmud 외

In the last several years, Twitter is being adopted by the companies as an alternative platform to interact with the customers to address their concerns. With the abundance of such unconventional conversation resources, …

Negation

What sentiment analysis can't see: Measuring whether customers were helped, and what went wrong, across 70,000 support conversations

2026-06-18 · Jason Potteiger arxiv

Most companies read their customer support data at scale using sentiment analysis, which measures how customers sound rather than whether they were satisfied with the result. We tested a richer alternative on 70,450 supp…

Sentiment Analysis

Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11

2023-04-25 · James Gung, Raphael Shu, Emily Moeng, Wesley Rose 외

With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states. H…