Filters








294,622 Hits in 4.3 sec

On Reliability of Patch Correctness Assessment

Dinh Xuan Bach Le, Lingfeng Bao, David Lo, Xin Xia, Shanping Li, Corina Pasareanu
2019 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)  
We do this by first constructing a gold set of correctness labels for 189 randomly selected patches generated by 8 state-of-the-art ASR techniques through a user study involving 35 professional developers  ...  To assess patch correctness, researchers have been following two methods separately: (1) Automated annotation, wherein patches are automatically labeled by an independent test suite (ITS)a patch passing  ...  Independent test suites obtained via an automatic test case generation tool are used to determine correctness label of a patch -see for example [17] , [19] .  ... 
doi:10.1109/icse.2019.00064 dblp:conf/icse/LeB00LP19 fatcat:7kkxmyrsezaidgkhg2d72vx3nq

On Reliability of Patch Correctness Assessment [article]

Xuan Bach D. Le, Lingfeng Bao, David Lo, Xin Xia, Shanping Li
2018 arXiv   pre-print
We do this by first constructing a gold set of correctness labels for 189 randomly selected patches generated by 8 state-of-the-art ASR techniques through a user study involving 35 professional developers  ...  To assess patch correctness, researchers have been following two typical ways separately: (1) Automated annotation, wherein patches are automatically labeled by an independent test suite (ITS) - a patch  ...  Independent test suites obtained via an automatic test case generation tool are used to determine correctness label of a patch -see for example [38, 63] .  ... 
arXiv:1805.05983v2 fatcat:7dadqreiwzaubgczwtia4ikhkm

Automatic Generation of Web-Based User Studies to Evaluate Depth Perception in Vascular Surface Visualizations

Monique Meuschke, Noeska N. Smit, Nils Lichtenberg, Bernhard Preim, Kai Lawonn
2018 Eurographics Workshop on Visual Computing for Biomedicine  
This approach helps to reduce effort in the setup of user studies themselves, and at the same time leverages a web-based approach that can help researchers attract more participants to their study.  ...  In addition, it can be challenging to reach enough participants to support the contribution claims of the paper.  ...  This depends on the position of the associated labels. To check the quality of our labeling algorithm, we conducted a user study with 14 participants (6 female, 8 male; age range from 23 to 35).  ... 
doi:10.2312/vcbm.20181227 dblp:conf/vcbm/MeuschkeSLPL18 fatcat:rzngn6dmgbfr7m5by2mjiqmyf4

Crowdsourcing visual detectors for video search

Bauke Freiburg, Jaap Kamps, Cees G.M. Snoek
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
In this paper, we study social tagging at the video fragmentlevel using a combination of automated content understanding and the wisdom of the crowds.  ...  To answer this question, we perform a 3-month online field study with a concert video search engine targeted at a dedicated user-community of pop concert enthusiasts.  ...  CROWDSOURCING CASE STUDY We study the merit of crowdsourcing visual detectors for video search within a cultural heritage context.  ... 
doi:10.1145/2072298.2071901 dblp:conf/mm/FreiburgKS11 fatcat:snb5am33bjfepiujtbwgjxuz2m

Automatic identification of speaker role and agreement/disagreement in broadcast conversation

Wen Wang, Sibel Yaman, Kristin Precoda, Colleen Richey
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Recently, Hutchinson et al. [3] studied speaker role labeling in English and Mandarin BC audio data as an  ...  We develop annotation approaches for a variety of linguistic phenomena.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA  ... 
doi:10.1109/icassp.2011.5947618 dblp:conf/icassp/WangYPR11 fatcat:qfl7kxkarfbzlmeiondtqrhcom

Unsupervised Labeling of Noun Clusters [chapter]

Theresa Jickels, Grzegorz Kondrak
2006 Lecture Notes in Computer Science  
The evaluation is performed using labels assigned to noun clusters by several participants of a specially designed human study.  ...  Semantic knowledge is important in many areas of natural language processing. We propose a new unsupervised learning algorithm to annotate groups of nouns with hypernym labels.  ...  Acknowledgments Thanks to Dekang Lin for sharing the dependency data and the LaTaT package, to Patrick Pantel for running his system on our test set, and to the participants of the human study for devoting  ... 
doi:10.1007/11766247_24 fatcat:53ra5jikffclfbxznmzxegfkoe

On the Automatic Evaluation of Social Exemplars

Luigi Castelli, Cristina Zogmaister, Eliot R. Smith, Luciano Arcuri
2004 Journal of Personality and Social Psychology  
Studies 1 and 2 confirmed the hypothesis that once an exemplar has been encoded as a member of a given group, at a later encounter the evaluation associated with the group will be unintentionally retrieved  ...  The present article focuses on the automatic evaluation of exemplars whose category membership has been learned in the past.  ...  In the present study, participants were shown photographs of members of a positive and a negative social group.  ... 
doi:10.1037/0022-3514.86.3.373 pmid:15008643 fatcat:neza5vk2bjbbjljtzakoc4mbkm

Towards a flexible platform for voice accent and expression selection on a Healthcare Robot

Aleksandar Igic, Catherine I. Watson, Jonathan Teutenberg, Elizabeth Broadbent, Rie Tamagawa, Bruce A. MacDonald
2009 Australasian Language Technology Association Workshop  
In the application of robots in healthcare, where there is a requirement to communicate vocally with non-expert users, a capacity to generate intelligible and expressive speech is needed.  ...  Expression is added to speech by modifying mean pitch and pitch range parameters of a statistical model distributed with Festival.  ...  The study group comprised of 20 participants, 6 males and 14 females with a mean age of 31.95 and standard deviation of 11.65.  ... 
dblp:conf/acl-alta/IgicWTBTM09 fatcat:hvbwyugyhbe3tlf77fgicmix3q

Evaluating Automatic Spreadsheet Metadata Extraction on a Large Set of Responses from MOOC Participants

Sohon Roy, Felienne Hermans, Efthimia Aivaloglou, Jos Winter, Arie van Deursen
2016 2016 IEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering (SANER)  
-Evaluating Automatic Spreadsheet Metadata Extraction on a Large Set of Responses from MOOC Participants TUD-SERG-2016-002 7  ...  Hence in this paper, we describe the collection of a large number of user responses regarding identification of spreadsheet metadata from participants of a MOOC.  ...  The Pilot phase was intended as a trial in order to gauge the level of involvement from the participants and to assess if such a game could yield sufficient data that can be used for a study.  ... 
doi:10.1109/saner.2016.98 dblp:conf/wcre/RoyHAWD16 fatcat:rod3ynvqn5gxha2qmdqmgs3gva

The Partnership of Citizen Science and Machine Learning: Benefits, Risks, and Future Challenges for Engagement, Data Collection, and Data Quality

Maryam Lotfian, Jens Ingensand, Maria Antonia Brovelli
2021 Sustainability  
We reviewed several use cases from various domains and categorized them according to the ML technique used and the impact of ML on citizen science in each project.  ...  The integration of AI and citizen science has mostly been used in biodiversity projects, with the primary focus on using citizen science data to train machine learning (ML) algorithms for automatic species  ...  A well-known example in ecological studies is the use of camera traps to automatically capture images of species [53] .  ... 
doi:10.3390/su13148087 fatcat:3zk4bgcecregbmfxfw2vegmd74

Hunting for headings

Jeremy T. Brudvik, Jeffrey P. Bigham, Anna C. Cavender, Richard E. Ladner
2008 Proceedings of the 10th international ACM SIGACCESS conference on Computers and accessibility - Assets '08  
In a user study in which sighted participants labeled headings on a set of web pages, participants did not often agree on which elements on the page should be labeled as headings, suggesting why headings  ...  Its performance in labeling headings compares favorably with both a manually-classified set of heading examples and the combined results of the sighted labelers in our study.  ...  Clearly, not all of the headings labeled by participants are likely to be good headings, especially in the cases where very few people agreed.  ... 
doi:10.1145/1414471.1414508 dblp:conf/assets/BrudvikBCL08 fatcat:niswf24vrfc4zoufpcbvfu5mne

Inducing a Stroop Effect

Emmanuel M. Pothos, Katy Tapper
2009 Applied Cognitive Psychology  
To examine this proposal, we trained participants to associate a meaningless label with either one other word or several other words and examined the induced Stroop interference for these meaningless labels  ...  We examine the conditions that lead to Stroop interference for a meaningless linguistic label.  ...  ACKNOWLEDGEMENTS This research was partly supported by grant ReF05/1/010 from the Wales Office of Research and Development (WORD).  ... 
doi:10.1002/acp.1603 fatcat:ykbmswxncvajvhq3uwujadokgq

Automatic Labelling of References for Internet Information Systems [chapter]

A. Geyer-Schulz, M. Hahsler
2000 Studies in Classification, Data Analysis, and Knowledge Organization  
A possible remedy is to complement the references with automatically generated labels which provide valuable information about the referenced information source.  ...  To solve these problems automatically we sketch for each problem a pragmatic mix of machine learning methods and report selected results.  ...  The next question was whether the concept behind a label is understandable. 67% of the test participants linked the "Revised"-label intuitively with the right concept of marking recently changed information  ... 
doi:10.1007/978-3-642-57280-7_49 fatcat:hbg4424tizaojjufmk742rvkti

The PViz comprehension tool for social network privacy settings

Alessandra Mazzia, Kristen LeFevre, Eytan Adar
2012 Proceedings of the Eighth Symposium on Usable Privacy and Security - SOUPS '12  
Because the user must be able to identify and distinguish automatically-constructed groups, we also address the important sub-problem of producing effective group labels.  ...  Utilizing feedback from the user study, we further iterated on our design, constructing PViz 2.0, and conducted a follow-up study to evaluate our refinements.  ...  The participants examined a total of 204 clusters, and selected a label for 53% of these clusters. Figure 4 summarizes the results for the cases where the user selected a label.  ... 
doi:10.1145/2335356.2335374 dblp:conf/soups/MazziaLA12 fatcat:tznbivn6pvaydfmncxuq25optm

"I Can't Lie Anymore!": The Implications of Location Automation for Mobile Social Applications

Sami Vihavainen, Antti Oulasvirta, Risto Sarvas
2009 Proceedings of the 6th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services  
Our observations come from a case study of Jaiku, a mobile microblogging service that automates disclosure and diffusion of location information.  ...  of the matter.  ...  We present a case study of Jaiku to provide first data on this matter.  ... 
doi:10.4108/icst.mobiquitous2009.6847 dblp:conf/mobiquitous/VihavainenOS09 fatcat:eob4eklfzbaepgvfqqwdufmkuu
« Previous Showing results 1 — 15 out of 294,622 results