Web Survey Bibliography
Title Human vs. artificial intelligence: Are software solutions already able to replace human beings?
Author Koch, M.
Year 2016
Access date 29.04.2016
Full text PDF (537MB)
Abstract
Relevance & Research Question: Human-based coding of open-ended answers is a time-consuming and tedious procedure – especially in terms of large sample sizes. Therefore, in recent years, several software solutions have been developed in order to enable an automatic process of coding. The objective of this study is to investigate if these software solutions can already replace human-based coding or if they should only be used as supportive tools.
Methods & Data: In the first step, verbatims were coded by two different people in order to calculate a basis value for inter-rater reliability: therefore, the coders independently assigned the answers to 14 predefined categories. In the next step, three software solutions (one freeware and two commercial software) were used for coding the open-ended answers: All three software programs were applied to cluster the open-ended answers based on the semantics (no predefined categories), while one of the two commercial software was also able to automatically allocate the answers to the 14 predefined categories. For analysis, the different types of coding were compared with each other (human – human, human-machine and machine-machine).
Results: Human-human: The human-based coding achieved the highest matching rate (M=86%; average Cohen’s kappa к=0,8). Human-machine: The clustering of the open-ended answers by their semantics delivered different thematic codes. However, one code was evident with all three software solutions and the human-based coding. Yet, the level of average agreement was rather low (M= 25%; Kappa к=0,3). In contrast to that, the machine-based allocation to the predefined categories performed better: the average inter-rater reliability was к=0,4 with 38% percent of agreement. Machine-machine: In terms of the code that was evident with all three software, an average agreement of 71% could be achieved between the three different programs (average Kappa к=0,6).
Added Value: In consideration of the results, it seems that human-based coding is much more precise than machine-based coding. Yet, software solutions can facilitate the tedious procedure of coding: They can be applied before coding in order to get an overview of important keywords and thematic aspects within seconds. Besides, the categorization via predefined categories is also promising.
Methods & Data: In the first step, verbatims were coded by two different people in order to calculate a basis value for inter-rater reliability: therefore, the coders independently assigned the answers to 14 predefined categories. In the next step, three software solutions (one freeware and two commercial software) were used for coding the open-ended answers: All three software programs were applied to cluster the open-ended answers based on the semantics (no predefined categories), while one of the two commercial software was also able to automatically allocate the answers to the 14 predefined categories. For analysis, the different types of coding were compared with each other (human – human, human-machine and machine-machine).
Results: Human-human: The human-based coding achieved the highest matching rate (M=86%; average Cohen’s kappa к=0,8). Human-machine: The clustering of the open-ended answers by their semantics delivered different thematic codes. However, one code was evident with all three software solutions and the human-based coding. Yet, the level of average agreement was rather low (M= 25%; Kappa к=0,3). In contrast to that, the machine-based allocation to the predefined categories performed better: the average inter-rater reliability was к=0,4 with 38% percent of agreement. Machine-machine: In terms of the code that was evident with all three software, an average agreement of 71% could be achieved between the three different programs (average Kappa к=0,6).
Added Value: In consideration of the results, it seems that human-based coding is much more precise than machine-based coding. Yet, software solutions can facilitate the tedious procedure of coding: They can be applied before coding in order to get an overview of important keywords and thematic aspects within seconds. Besides, the categorization via predefined categories is also promising.
Access/Direct link Conference Homepage (presentation)
Year of publication2016
Bibliographic typeConferences, workshops, tutorials, presentations
Web survey bibliography - Germany (361)
- Interviewer effects on onliner and offliner participation in the German Internet Panel; 2017; Herzing, J. M. E.; Blom, A. G.; Meuleman, B.
- Comparing the same Questionnaire between five Online Panels: A Study of the Effect of Recruitment Strategy...; 2017; Schnell, R.; Panreck, L.
- Push2web or less is more? Experimental evidence from a mixed-mode population survey at the community...; 2017; Neumann, R.; Haeder, M.; Brust, O.; Dittrich, E.; von Hermanni, H.
- Social Desirability and Undesirability Effects on Survey Response latencies; 2017; Andersen, H.; Mayerl, J.
- Comparison of response patterns in different survey designs: a longitudinal panel with mixed-mode and...; 2017; Ruebsamen, N.; Akmatov, M. K.; Castell, S.; Karch, A.; Mikolajczyk, R. T.
- Mobile Research im Kontext der digitalen Transformation; 2017; Friedrich-Freksa, M.
- Kognitives Pretesting; 2017; Neuert, C.
- Grundzüge des Datenschutzrechts und aktuelle Datenschutzprobleme in der Markt- und Sozialforschung; 2017; Schweizer, A.
- Article Establishing an Open Probability-Based Mixed-Mode Panel of the General Population in Germany...; 2017; Bosnjak, M.; Dannwolf, T.; Enderle, T.; Schaurer, I.; Struminskaya, B.; Tanner, A.; Weyandt, K.
- Socially Desirable Responding in Web-Based Questionnaires: A Meta-Analytic Review of the Candor Hypothesis...; 2016; Gnambs, T.; Kaspar, K.
- Methodological Aspects of Central Left-Right Scale Placement in a Cross-national Perspective; 2016; Scholz, E.; Zuell, C.
- Predicting and Preventing Break-Offs in Web Surveys; 2016; Mittereder, F.
- Incorporating eye tracking into cognitive interviewing to pretest survey questions; 2016; Neuert, C.; Lenzner, T.
- Geht’s auch mit der Maus? – Eine Methodenstudie zu Online-Befragungen in der Jugendforschung...; 2016; Heim, R.; Konowalczyk, S.; Grgic, M.; Seyda, M.; Burrmann, U.; Rauschenbach, T.
- Comparing Cognitive Interviewing and Online Probing: Do They Find Similar Results?; 2016; Meitinger, K., Behr, D.
- Device Effects - How different screen sizes affect answers in online surveys; 2016; Fisher, B.; Bernet, F.
- Effects of motivating question types with graphical support in multi channel design studies; 2016; Luetters, H.; Friedrich-Freksa, M.; Vitt, SGoldstein, D. G.
- Analyzing Cognitive Burden of Survey Questions with Paradata: A Web Survey Experiment; 2016; Hoehne, J. K.; Schlosser, S.; Krebs, D.
- Secondary Respondent Consent in the German Family Panel; 2016; Schmiedeberg, C.; Castiglioni, L.; Schroeder, J.
- Does Changing Monetary Incentive Schemes in Panel Studies Affect Cooperation? A Quasi-experiment on...; 2016; Schaurer, I.; Bosnjak, M.
- Using Cash Incentives to Help Recruitment in a Probability Based Web Panel: The Effects on Sign Up Rates...; 2016; Krieger, U.
- The Mobile Web Only Population: Socio-demographic Characteristics and Potential Bias ; 2016; Fuchs, M.; Metzler, A.
- The Impact of Scale Direction, Alignment and Length on Responses to Rating Scale Questions in a Web...; 2016; Keusch, F.; Liu, M.; Yan, T.
- Web Surveys Versus Other Survey Modes: An Updated Meta-analysis Comparing Response Rates ; 2016; Wengrzik, J.; Bosnjak, M.; Lozar Manfreda, K.
- Retrospective Measurement of Students’ Extracurricular Activities with a Self-administered Calendar...; 2016; Furthmueller, P.
- Privacy Concerns in Responses to Sensitive Questions. A Survey Experiment on the Influence of Numeric...; 2016; Bader, F., Bauer, J., Kroher, M., Riordan, P.
- Ballpoint Pens as Incentives with Mail Questionnaires – Results of a Survey Experiment; 2016; Heise, M.
- Does survey mode matter for studying electoral behaviour? Evidence from the 2009 German Longitudinal...; 2016; Bytzek, E.; Bieber, I. E.
- Forecasting proportional representation elections from non-representative expectation surveys; 2016; Graefe, A.
- Setting Up an Online Panel Representative of the General Population The German Internet Panel; 2016; Blom, A. G.; Gathmann, C.; Krieger, U.
- Online Surveys are Mixed-Device Surveys. Issues Associated with the Use of Different (Mobile) Devices...; 2016; Toepoel, V.; Lugtig, P. J.
- Stable Relationships, Stable Participation? The Effects of Partnership Dissolution and Changes in Relationship...; 2016; Mueller, B.; Castiglioni, L.
- Will They Stay or Will They Go? Personality Predictors of Dropout in Online Study; 2016; Nestler, S.; Thielsch, M.; Vasilev, E.; Back, M.
- Respondent Conditioning in Online Panel Surveys: Results of Two Field Experiments; 2016; Struminskaya, B.
- A Privacy-Friendly Method to Reward Participants of Online-Surveys; 2015; Herfert, M.; Lange, B.; Selzer, A.; Waldmann, U.
- The impact of frequency rating scale formats on the measurement of latent variables in web surveys -...; 2015; Menold, N.; Kemper, C. J.
- Investigating response order effects in web surveys using eye tracking; 2015; Karem Hoehne, J.; Lenzner, T.
- Implementation of the forced answering option within online surveys: Do higher item response rates come...; 2015; Decieux, J. P.; Mergener, A.; Neufang, K.; Sischka, P.
- Translating Answers to Open-ended Survey Questions in Cross-cultural Research: A Case Study on the Interplay...; 2015; Behr, D.
- The Effects of Questionnaire Completion Using Mobile Devices on Data Quality. Evidence from a Probability...; 2015; Bosnjak, M.; Struminskaya, B.; Weyandt, K.
- Are they willing to use the web? First results of a possible switch from PAPI to CAPI/CAWI in an establishment...; 2015; Ellguth, P.; Kohaut, S.
- Measuring Political Knowledge in Web-Based Surveys: An Experimental Validation of Visual Versus Verbal...; 2015; Munzert, S.; Selb, P.
- Changing from CAPI to CAWI in an ongoing household panel - experiences from the German Socio-Economic...; 2015; Schupp, J.; Sassenroth, D.
- Rating Scales in Web Surveys: A Test of New Drag-and-Drop Rating Procedures; 2015; Kunz, T.
- Mode System Effects in an Online Panel Study: Comparing a Probability-based Online Panel with two Face...; 2015; Struminskaya, B.; De Leeuw, E. D.; Kaczmirek, L.
- Higher response rates at the expense of validity? Consequences of the implementation of the ‘forced...; 2015; Decieux, J. P.; Mergener, A.; Neufang, K.; Sischka, P.
- A quasi-experiment on effects of prepaid versus promised incentives on participation in a probability...; 2015; Schaurer, I.; Bosnjak, M.
- Response Effects of Prenotification, Prepaid Cash, Prepaid Vouchers, and Postpaid Vouchers: An Experimental...; 2015; van Veen, F.; Goeritz, A.; Sattler, S.
- Recruiting Respondents for a Mobile Phone Panel: The Impact of Recruitment Question Wording on Cooperation...; 2015; Busse, B.; Fuchs, M.
- The Influence of the Answer Box Size on Item Nonresponse to Open-Ended Questions in a Web Survey ; 2015; Zuell, C.; Menold, N.; Koerber, S.