Expertise Modeling and Recommendation in Online Question and Answer Forums

Budalakoti, Suratna; DeAngelis, David; Barber, K. Suzanne

doi:10.1109/cse.2009.62

Cited by 7 publications

(5 citation statements)

References 13 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most studies about RSs in online Q&A forums focus on general aspects rather than a specific subject such as healthcare. Budalakoti et al [15] present a RS with three different methods for selecting the most appropriate responder given a question on Yahoo! Answer.…”

Section: Related Workmentioning

confidence: 99%

Posting Recommendations in Healthcare Q&A Forums

2021

View full text Add to dashboard Cite

Online Q&A forums, unlike search engines, allow posting of various types of queries, thus attracting users to seek information and solve problems in specific domains. However, as insufficient knowledge leads to incomprehensible queries, unsuitable responses are common. We develop posting recommendation systems (RSs) to support users in composing reasonable posts and receiving effective answers. The posting RSs were evaluated by a user study containing 27 participants and three tasks to examine if users engaged more in the question generation process. Two medical experts were recruited to verify whether professionals can understand and answer posts supported by RSs. The results show that the proposed mechanism enables askers to produce posts with better understandability, which leads experts to devote more attention to answer their questions.

show abstract

Section: Related Workmentioning

confidence: 99%

Posting Recommendations in Healthcare Q&A Forums

2021

View full text Add to dashboard Cite

show abstract

“…The reason why term frequency (tf) is not used is due to that each question usually contains a few words while each word often has a unique occurrence, thus the tf of a word is usually 0 or 1. The idf of term w j in q i is calculated as: (3) where N bg is the number of questions in Ω bg , and qf i is the question frequency, calculated as the number of questions in which w j occurs in Ω bg .…”

Section: Problem Statementmentioning

confidence: 99%

“…Modeling question popularity is beneficial to lots of applications like: a) For the task of question recommendation [3] [18], popular questions should have higher priorities to be recommended to expert users since such questions are more attractive and are more likely to receive responses from expert users; and b) the most popular questions can be discovered and displayed on the homepages of community QA websites so as to attract more users. In this paper, we employ logistic regression [12] to predict whether a given question is popular.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards modeling question popularity in community question answering

Wenyin

2012

2012 IEEE 11th International Conference on Cognitive Informatics and Cognitive Computing

View full text Add to dashboard Cite

Community question answering (QA) has become increasingly popular and received a great variety of questions every day. Among them, some questions are very attractive and popular to many users, while some other questions are very tedious and unattractive. In this paper, we aim to identify popular questions in the community QA through modeling question popularity. Three popularity-related features of questions are defined to build the popularity model: (a) potential hits, which reflect how many users are attracted by a question at their first glance; (b) popular terms, from which users find a question attractive; and (c) tedious unpopular terms. The notable characteristic of the proposed framework is extensibility and more features can be incorporated. A large-scale question dataset from a practical community QA website was used to train and test the model. Meanwhile, two well-known classifiers, k-nearest neighbors and support vector machines, were implemented for comparison. Our approach is well validated by the experimental results with much higher prediction accuracy than the baseline methods.

show abstract

“…A similar approach has been made at Yahoo! Answers by Dror et al (2011) and Budalakoti et al (2009), who identify users who are most capable of providing a satisfactory answer to specific questions.…”

Section: Question and Answers Support Programs With Recommender Systemsmentioning

confidence: 99%

The Skills, Competences, and Attitude toward Information and Communications Technology Recommender System: an online support program for teachers with personalized recommendations

Muñoz

Penalba

Sánchez

2015

New Review of Hypermedia and Multimedia

View full text Add to dashboard Cite

Teachers deal with Information and Communications Technology (ICT) every day and they often have to solve problems by themselves. To help them in coping with this issue, an online support program has been created, where teachers can pose their problems on ICT and they can receive solutions from other teachers. A Recommender System has been defined and implemented into the support program to suggest each teacher the most suitable solution based on her Skills, Competences and Attitude towards ICT (SCAT-ICT). The support program has been initially populated with 70 problems from 86 teachers. Then 30 teachers grouped these problems into 6 categories with the card sorting technique. Real solutions to these problems have been proposed by 25 trained teachers. Finally, 17 teachers have evaluated the usability of the support program and the Recommender System, where results showed a high score on the standardized System Usability Scale.

show abstract

Expertise Modeling and Recommendation in Online Question and Answer Forums

Cited by 7 publications

References 13 publications

Posting Recommendations in Healthcare Q&A Forums

Posting Recommendations in Healthcare Q&A Forums

Towards modeling question popularity in community question answering

The Skills, Competences, and Attitude toward Information and Communications Technology Recommender System: an online support program for teachers with personalized recommendations

Contact Info

Product

Resources

About