AUnet: An Unsupervised Method for Answer Reliability Evaluation in Community QA Systems

Ren, Ruoqing; Duan, Haimeng; Liu, Wenqiang; Liu, Jun

doi:10.1007/978-3-030-01298-4_24

Cited by 2 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quality of answers on SQAs can range from excellent to abysmal [15,16,[23][24][25]. A dominant strand of SQA research focuses on answer quality.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Existing research suggests that the problem primarily stems from the lack of adequate gate-keeping [11]. While some users post high quality answers out of altruism [12] and the motivation to gain recognition in the community [13,14], others could end up posting subpar answers due to either lack of domain knowledge or the deliberate motivation to abuse the functionality of SQAs [15,16]. Given the little editorial control, separating high quality answers from those that are subpar is challenging.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering Sites

Roy

Ahmad

Singh

et al. 2022

IETE Journal of Research

View full text Add to dashboard Cite

Social Question Answering sites (SQAs) are online platforms that allow Internet users to ask questions, and obtain answers from others in the community. SQAs have been marred by the problem of low-quality answers. Worryingly, answer quality on SQAs have been reported to be following a downward trajectory in recent years. To this end, existing research has predominantly focused on finding the best answer, or identifying high-quality answers among the available responses.However, such scholarly efforts have not reduced the volume of low-quality answers on SQAs. Therefore, the goal of this research is to extract features in order to weed out low-quality answers as soon as they are posted on SQAs. Data from Stack Exchange was used to carry out the investigation. Informed by the literature, 26 features were extracted. Thereafter, machine learning algorithms were implemented that could correctly identify 85% to 96% of low-quality answers. The key contribution of this research is the development of a system to detect subpar answers on the fly at the time of posting. It is intended to be used as an early warning system that warns users about answer quality at the point of posting. Lee et al. [27] assigned a score to each voter to capture the level of agreement among those who up-voted or down-voted answers. This voting score was used as a feature to predict the best answer. These works typically use machine learning-

show abstract

“…The quality of answers on SQAs can range from excellent to abysmal [15,16,[23][24][25]. A dominant strand of SQA research focuses on answer quality.…”

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering Sites

Roy

Ahmad

Singh

et al. 2022

IETE Journal of Research

View full text Add to dashboard Cite

show abstract

“…Inducing more and higher-quality answers is essential to sustainable development of SQA websites. To facilitate sustainable development of SQA websites, numerous researchers have studied user motivation in knowledge contribution (Wasko & Faraj, 2000), factors attracting or motivating answerers (Jin et al, 2015), criteria measuring question success or failure (Shah et al, 2012), searchresult relevance judgment , search-result measurement (Zhang et al, 2019), answer quality (Zhao et al, 2019), website evaluation (Huang et al, 2006), and solutions to improve response rate (Liu & Jansen,2017;Oh, 2018;Elalfy et al, 2017;Ren et al, 2018;Sin et al, 2018;Wang, et al, 2018;Li et al, 2016). However, little is known about how the question itself affects the answer outcome on an SQA website.…”

Section: Introductionmentioning

confidence: 99%

How Question Characteristics Impact Answer Outcomes on Social Question-and-Answer Websites

Zhao

Zhang

et al. 2021

Journal of Global Information Management

View full text Add to dashboard Cite

Inducing more and higher-quality answers to questions is essential to sustainable development of Social Question-and-Answer (SQA) websites. Previous research has studied factors affecting question success and user motivation in answering questions, but how a question’s own characteristics affect the question’s answer outcome on SQA websites remains unknown. This study examines the impact of the characteristics of a question, namely readability, emotionality, additional descriptions, and question type, on the question’s answer outcome as measured by number of answers, average answer length, and number of “likes” received by answers to the question. Regression analyses reveal that readability, additional descriptions, and question type have significant impact on multiple measurements of answer outcome, while emotionality only affects the average answer length. This study provides insights to SQA website builders as they instruct users on question construction. It also provides insights to SQA website users on how to induce more and higher-quality answers to their questions.

show abstract

AUnet: An Unsupervised Method for Answer Reliability Evaluation in Community QA Systems

Cited by 2 publications

References 18 publications

Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering Sites

Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering Sites

How Question Characteristics Impact Answer Outcomes on Social Question-and-Answer Websites

Contact Info

Product

Resources

About