Show simple item record

dc.contributor.authorSameki, Mehrnooshen_US
dc.contributor.authorGentil, Mattiaen_US
dc.contributor.authorMays, Kate K.en_US
dc.contributor.authorGuo, Leien_US
dc.contributor.authorBetke, Margriten_US
dc.date.accessioned2019-09-03T18:08:23Z
dc.date.available2019-09-03T18:08:23Z
dc.date.issued2016
dc.identifierhttp://arxiv.org/abs/1608.08953v2
dc.identifier.citationMehrnoosh Sameki, Mattia Gentil, Kate K Mays, Lei Guo, Margrit Betke. 2016. "Dynamic Allocation of Crowd Contributions for Sentiment Analysis during the 2016 U.S. Presidential Election." http://arxiv.org/abs/1608.08953v2
dc.identifier.urihttps://hdl.handle.net/2144/37630
dc.description.abstractOpinions about the 2016 U.S. Presidential Candidates have been expressed in millions of tweets that are challenging to analyze automatically. Crowdsourcing the analysis of political tweets effectively is also difficult, due to large inter-rater disagreements when sarcasm is involved. Each tweet is typically analyzed by a fixed number of workers and majority voting. We here propose a crowdsourcing framework that instead uses a dynamic allocation of the number of workers. We explore two dynamic-allocation methods: (1) The number of workers queried to label a tweet is computed offline based on the predicted difficulty of discerning the sentiment of a particular tweet. (2) The number of crowd workers is determined online, during an iterative crowd sourcing process, based on inter-rater agreements between labels.We applied our approach to 1,000 twitter messages about the four U.S. presidential candidates Clinton, Cruz, Sanders, and Trump, collected during February 2016. We implemented the two proposed methods using decision trees that allocate more crowd efforts to tweets predicted to be sarcastic. We show that our framework outperforms the traditional static allocation scheme. It collects opinion labels from the crowd at a much lower cost while maintaining labeling accuracy.en_US
dc.language.isoen_US
dc.subjectHuman-computer interactionen_US
dc.subjectComputation and languageen_US
dc.subjectSocial and information networksen_US
dc.titleDynamic allocation of crowd contributions for sentiment analysis during the 2016 U.S. presidential electionen_US
dc.typeArticleen_US
dc.description.versionFirst author draften_US
pubs.elements-sourcemanual-entryen_US
pubs.notes10 pages, 3 figuresen_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Arts & Sciencesen_US
pubs.organisational-groupBoston University, College of Arts & Sciences, Department of Computer Scienceen_US
pubs.publication-statusUnpublisheden_US
dc.identifier.orcid0000-0002-4491-6868 (Betke, Margrit)
dc.identifier.mycv354844


This item appears in the following Collection(s)

Show simple item record