Abstract | ||
---|---|---|
This paper reports on an investigation into outstanding and ordinary users of two Question & Answer (Q&A) communities. Considering some behavior perspectives such as participation, linguistic traits, social ties, influence, and focus, we found that outstanding users (i) are more likely to engage in discussions; (ii) tend to use more sophisticated linguistic traits; (iii) generate longer debates; (iv) value the diversity of their connections; and (v) participate in several topics, rather than one specialist niche. These findings allow us to use behavioral patterns to predict if a given user is outstanding and predict which answer gives a definitive solution for a question. Then, we present two feature learning methods to automatically generate the inputs for the prediction model to classify users as outstanding or ordinary. Our feature learning approaches outperformed related methods and generated competitive results when compared to feature engineering based on behavioral patterns.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3342220.3344928 | Proceedings of the 30th ACM Conference on Hypertext and Social Media |
Keywords | Field | DocType |
graph analysis, interaction analysis, learning behavior, machine learning, q&a community analysis | World Wide Web,Computer science,Multimedia | Conference |
ISBN | Citations | PageRank |
978-1-4503-6885-8 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thiago Baesso Procaci | 1 | 15 | 3.08 |
Sean Siqueira | 2 | 1 | 1.38 |
Bernardo Pereira Nunes | 3 | 185 | 30.96 |
Ujwal Gadiraju | 4 | 59 | 10.46 |