Data Mining - Concepts and Techniques.

The Structural Transformation of the Public Sphere: An Inquiry into a Category of Bourgeois Society

行銷硏究 : Marketing research

The theory of affordances

What is Twitter

Users are rapidly turning to social media to request and receive customer service; however, a majority of these requests were not addressed timely or even not addressed at all. To overcome the problem, we create a new conversational system to automatically generate responses for users requests on social media. Our system is integrated with state-of-the-art deep learning techniques and is trained by nearly 1M Twitter conversations between users and agents from over 60 brands. The evaluation reveals that over 40% of the requests are emotional, and the system is about as good as human agents in showing empathy to help users cope with emotional situations. Results also show our system outperforms information retrieval system based on both human judgments and an automatic evaluation metric.

A New Chatbot for Customer Service on Social Media

Chatbot has become an important solution to rapidly increasing customer care demands on social media in recent years. However, current work on chatbot for customer care ignores a key to impact user experience - tones. In this work, we create a novel tone-aware chatbot that generates toned responses to user requests on social media. We first conduct a formative research, in which the effects of tones are studied. Significant and various influences of different tones on user experience are uncovered in the study. With the knowledge of effects of tones, we design a deep learning based chatbot that takes tone information into account. We train our system on over 1.5 million real customer care conversations collected from Twitter. The evaluation reveals that our tone-aware chatbot generates as appropriate responses to user requests as human agents. More importantly, our chatbot is perceived to be even more empathetic than human agents.

Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media

With the noted popularity of social networking sites, people increasingly rely on these social networks to address their information needs. Although social question and answering is potentially an important venue seeking information online, it, unfortunately, suffers from a problem of low response rate, with the majority of questions receiving no response. To understand why the response rate of social question and answering is low and hopefully to increase it in the future, this research analyzes extrinsic factors that may influence the response probability of questions posted on Sina Weibo. We propose 17 influential factors from 2 different perspectives: the content of the question, and the characteristics of the questioner. We also train a prediction model to forecast a question's likelihood of being responded based on the proposed features We test our predictive model on more than 60,000 real-world questions posted on Weibo, which generate more than 600,000 responses. Findings show that a Weibo's question answerability is primarily contingent on the questioner versus the question. Our findings indicate that using appreciation emojis can increase a question's response probability, whereas the use of hashtags negatively influences the chances of receiving answers. Our contribution is in providing insights for the design and development of future social question and answering tools, as well as for enhancing social network users’ collaboration in supporting social information seeking activities.

Questioner or question: Predicting the response rate in social question and answering on Sina Weibo

Evaluate the effectiveness of question routing systems in the social Q&A process.Find that individuals are more willing to share their knowledge under question routing context whereas less connected.Build an effective model to automatically identify active knowledge sharers from non-shares using non-Q&A features from four dimensions: profile, posting behavior, language style, and social activities. The increasing volume of questions posted on social question and answering sites has triggered the development of question routing services. Most of these routing algorithms are able to recognize effectively individuals with the required knowledge to answer a specific question. However, just because people have the capability to answer a question, does not mean that they have the desire to help. In this research, we evaluate the practical performance of the question routing services in social context by analyzing the knowledge sharing behavior of users in social Q&A process in terms of their participation, interests, and connectedness. We collect questions and answers over a ten-month period from Wenwo, a major Chinese question routing service. Using 340,658 questions and 1,754,280 replies, findings reveal separate roles for knowledge sharers and consumers. Based on this finding, we identify knowledge sharers from non-sharers a priori in order to increase the response probabilities. We evaluate our model based on an analysis of 3006 Wenwo knowledge sharers and non-sharers. Our experimental results demonstrate knowledge sharer prediction based solely on non-Q&A features achieves a 70% success rate in accurately identifying willing respondents.

Identifying and predicting the desire to help in social question and answering

With the increasing growth and popularity of social networking sites, social question and answering has become a venue for individuals to seek and share information. This study evaluates eleven extrinsic factors that may influence the response rate in social question and answering. These factors include the number of followers, the frequency of posting, the number of at-mentioned recipients, whether or not a question contains an at-mentioned verified account, unverified account, hashtag, emoticon, expression of gratitude, repeated punctuation or interjections, as well as the topic and the posting time of a question. We collected and analyzed over 10,000 questions from Sina Weibo. Eight out of all eleven features were found to significantly predict the number of responses received. We believe that our study is of significant value in providing insights for the design and development of future social question and answering tools, as well as enhancing the collaboration among social network users in supporting social information seeking activities.

/pdf/factors-influencing-the-response-rate-in-social-question-and-1yvfn84xje.pdf

Zhe Liu

Papers

A New Chatbot for Customer Service on Social Media

Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media

Questioner or question: Predicting the response rate in social question and answering on Sina Weibo

Identifying and predicting the desire to help in social question and answering

Factors influencing the response rate in social question and answering behavior