| 000 | 03125nlm0a2200385 4500 | ||
|---|---|---|---|
| 001 | 659541 | ||
| 005 | 20231030041632.0 | ||
| 035 | _a(RuTPU)RU\TPU\network\28146 | ||
| 090 | _a659541 | ||
| 100 | _a20190226a2018 k y0engy50 ba | ||
| 101 | 0 | _aeng | |
| 105 | _ay z 100zy | ||
| 135 | _adrcn ---uucaa | ||
| 181 | 0 | _ai | |
| 182 | 0 | _ab | |
| 200 | 0 |
_aCrowd-based Multi-Predicate Screening of Papers in Literature Reviews _fE. Krivosheev, F. Casati, B. Benatallah |
|
| 203 |
_aText _celectronic |
||
| 300 | _aTitle screen | ||
| 330 | _aSystematic literature reviews (SLRs) are one of the most commonand useful form of scientific research and publication. Tens of thousands of SLRs are published each year, and this rate is growingacross all fields of science. Performing an accurate, complete andunbiased SLR is however a difficult and expensive endeavor. Thisis true in general for all phases of a literature review, and in particular for the paper screening phase, where authors filter a set ofpotentially in-scope papers based on a number of exclusion criteria.To address the problem, in recent years the research communityhas began to explore the use of the crowd to allow for a faster, accurate, cheaper and unbiased screening of papers. Initial results showthat crowdsourcing can be effective, even for relatively complexreviews. In this paper we derive and analyze a set of strategies for crowdbased screening, and show that an adaptive strategy, that continuously re-assesses the statistical properties of the problem to minimize the number of votes needed to take decisions for each paper,significantly outperforms a number of non-adaptive approachesin terms of cost and accuracy. We validate both applicability andresults of the approach through a set of crowdsourcing experiments, and discuss properties of the problem and algorithms thatwe believe to be generally of interest for classification problemswhere items are classified via a series of successive tests (as it oftenhappens in medicine). | ||
| 463 |
_tWorld Wide Web Conference (WWW 2018) _oproceedings, Lyon, France, April 23-27, 2018 _v[P. 55-64] _d2018 |
||
| 610 | 1 | _aтруды учёных ТПУ | |
| 610 | 1 | _aэлектронный ресурс | |
| 610 | 1 | _ahuman computation | |
| 610 | 1 | _aclassification | |
| 610 | 1 | _aliterature reviews | |
| 610 | 1 | _aвычисления | |
| 610 | 1 | _aклассификации | |
| 610 | 1 | _aобзоры литературы | |
| 700 | 1 |
_aKrivosheev _bE. _gEvgeny |
|
| 701 | 1 |
_aCasati _bF. _cItalian economist and Professor at the University of Trento (Italy) _cProfessor of Tomsk Polytechnic University, candidate of technical Sciences _f1971- _gFabio _2stltpush _3(RuTPU)RU\TPU\pers\39820 |
|
| 701 | 1 |
_aBenatallah _bB. _gBoualem |
|
| 712 | 0 | 2 |
_aНациональный исследовательский Томский политехнический университет _bШкола инженерного предпринимательства _c(2017- ) _h7949 _2stltpush _3(RuTPU)RU\TPU\col\23544 |
| 801 | 2 |
_aRU _b63413507 _c20190226 _gRCR |
|
| 856 | 4 | _uhttps://doi.org/10.1145/3178876.3186036 | |
| 942 | _cCF | ||