Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools
With the increase in usage of machine learning models within many different aspects of customer interactions, it has become very clear that bias detection within associated customer interaction datasets has led to a critical focus on issues such as the identification of bias prior to model building,...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10126086/ |
| _version_ | 1797808454709018624 |
|---|---|
| author | Andy Donald Apostolos Galanopoulos Edward Curry Emir Munoz Ihsan Ullah M. A. Waskow Maciej Dabrowski Manan Kalra |
| author_facet | Andy Donald Apostolos Galanopoulos Edward Curry Emir Munoz Ihsan Ullah M. A. Waskow Maciej Dabrowski Manan Kalra |
| author_sort | Andy Donald |
| collection | DOAJ |
| description | With the increase in usage of machine learning models within many different aspects of customer interactions, it has become very clear that bias detection within associated customer interaction datasets has led to a critical focus on issues such as the identification of bias prior to model building, lack of understanding and transparency within models, and ultimately the prevention of biased predictions or classifications. This has never been more important since the introduction of the EU General Data Protection Regulation (GDPR) and the associated rule of “right of explanation”. In this paper, we survey the state of the art for bias detection, avoidance and mitigation within datasets, and the associated methods and tools available. Our purpose is to establish an understanding of how established customer interaction-based use cases can utilise these techniques. The focus is primarily on tackling the bias in unstructured text data as a pre-process prior to the machine learning model training phase. We hope that this research encourages the further establishment of responsible usage of customer interaction datasets to allow the prevention of bias being introduced into machine learning pipelines and to also allow greater awareness of the potential for further research in this area. |
| first_indexed | 2024-03-13T06:37:45Z |
| format | Article |
| id | doaj.art-140b5c56bca04e7e9e3604fa879262bb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T06:37:45Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-140b5c56bca04e7e9e3604fa879262bb2023-06-08T23:01:24ZengIEEEIEEE Access2169-35362023-01-0111537035371510.1109/ACCESS.2023.327675710126086Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and ToolsAndy Donald0https://orcid.org/0009-0007-3307-2800Apostolos Galanopoulos1Edward Curry2https://orcid.org/0000-0001-8236-6433Emir Munoz3https://orcid.org/0000-0002-0089-8135Ihsan Ullah4https://orcid.org/0000-0002-7964-5199M. A. Waskow5https://orcid.org/0000-0001-7443-2920Maciej Dabrowski6Manan Kalra7Insight SFI Research Center for Data Analytics, University of Galway, Lower Dangan, Galway, IrelandGenesys Cloud Services Inc., Galway, IrelandInsight SFI Research Center for Data Analytics, University of Galway, Lower Dangan, Galway, IrelandGenesys Cloud Services Inc., Galway, IrelandInsight SFI Research Center for Data Analytics, University of Galway, Lower Dangan, Galway, IrelandInsight SFI Research Center for Data Analytics, University of Galway, Lower Dangan, Galway, IrelandGenesys Cloud Services Inc., Galway, IrelandGenesys Cloud Services Inc., Galway, IrelandWith the increase in usage of machine learning models within many different aspects of customer interactions, it has become very clear that bias detection within associated customer interaction datasets has led to a critical focus on issues such as the identification of bias prior to model building, lack of understanding and transparency within models, and ultimately the prevention of biased predictions or classifications. This has never been more important since the introduction of the EU General Data Protection Regulation (GDPR) and the associated rule of “right of explanation”. In this paper, we survey the state of the art for bias detection, avoidance and mitigation within datasets, and the associated methods and tools available. Our purpose is to establish an understanding of how established customer interaction-based use cases can utilise these techniques. The focus is primarily on tackling the bias in unstructured text data as a pre-process prior to the machine learning model training phase. We hope that this research encourages the further establishment of responsible usage of customer interaction datasets to allow the prevention of bias being introduced into machine learning pipelines and to also allow greater awareness of the potential for further research in this area.https://ieeexplore.ieee.org/document/10126086/Bias detectionmachine learningbias evaluationexplainable AI |
| spellingShingle | Andy Donald Apostolos Galanopoulos Edward Curry Emir Munoz Ihsan Ullah M. A. Waskow Maciej Dabrowski Manan Kalra Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools IEEE Access Bias detection machine learning bias evaluation explainable AI |
| title | Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools |
| title_full | Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools |
| title_fullStr | Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools |
| title_full_unstemmed | Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools |
| title_short | Bias Detection for Customer Interaction Data: A Survey on Datasets, Methods, and Tools |
| title_sort | bias detection for customer interaction data a survey on datasets methods and tools |
| topic | Bias detection machine learning bias evaluation explainable AI |
| url | https://ieeexplore.ieee.org/document/10126086/ |
| work_keys_str_mv | AT andydonald biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT apostolosgalanopoulos biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT edwardcurry biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT emirmunoz biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT ihsanullah biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT mawaskow biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT maciejdabrowski biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools AT manankalra biasdetectionforcustomerinteractiondataasurveyondatasetsmethodsandtools |