Dr Graham McDonald

  • Lecturer (Computing Science)

Biography

Research interests

My research interests include information retrieval and text classification. In particular, my research focuses on sensitive information retrieval and fair ranking strategies.

Sensitive Information: I research methods for automatically classifying sensitive information that is exempt from public release through freedom of information laws, and how such technologies can assist and learn from human sensitivity reviewers (for example in active learning and technology-assisted review scenarios). I am part of a consortium that is delivering the first large-scale digital sensitivity review system within UK government departments.

Fair Information Retrieval: I am an organiser of the TREC 2021 Fair Ranking Track. The track aims to provide a common research framework for researchers interested in developing fair ranking strategies that can provide an appropriate level of exposure to relevant information producers over time.

 

Further information is available on my personal webpage: here

and my Google Scholar profile here

Publications

List by: Type | Date

Jump to: 2022 | 2021 | 2020 | 2019 | 2018 | 2017
Number of items: 14.

2022

Narvala, H. , McDonald, G. and Ounis, I. (2022) Sensitivity Review of Large Collections by Identifying and Prioritising Coherent Documents Groups. In: Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM ’22), Atlanta, GA, USA, 17-21 October 2022, pp. 4931-4935. ISBN 9781450392365 (doi: 10.1145/3511808.3557182)

Narvala, H. , McDonald, G. and Ounis, I. (2022) The Role of Latent Semantic Categories and Clustering in Enhancing the Efficiency of Human Sensitivity Review. In: Seventh ACM SIGIR Conference on Human Information Interaction and Retrieval (ACM CHIIR 2022), Regensburg, Germany, 14-18 Mar 2022, pp. 56-66. ISBN 9781450391863 (doi: 10.1145/3498366.3505824)

McDonald, G. , Macdonald, C. and Ounis, I. (2022) Search results diversification for effective fair ranking in academic search. Information Retrieval Journal, 25(1), pp. 1-26. (doi: 10.1007/s10791-021-09399-z)

Frayling, E., Macdonald, C. , McDonald, G. and Ounis, I. (2022) Using Entities in Knowledge Graph Hierarchies to Classify Sensitive Information. In: 13th International Conference of the CLEF Association (CLEF 2022), Bologna, Italy, 5-8 Sept 2022, pp. 125-132. ISBN 9783031136429 (doi: 10.1007/978-3-031-13643-6_10)

2021

Narvala, H. , McDonald, G. and Ounis, I. (2021) RelDiff: Enriching Knowledge Graph Relation Representations for Sensitivity Classification. In: 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, 07-11 Nov 2021, pp. 3671-3681. ISBN 9781955917100

McDonald, G. , Macdonald, C. and Ounis, I. (2021) How the accuracy and confidence of sensitivity classification affects digital sensitivity review. ACM Transactions on Information Systems, 39(1), 4. (doi: 10.1145/3417334)

2020

McDonald, G. , Macdonald, C. and Ounis, I. (2020) Active Learning Stopping Strategies for Technology-Assisted Sensitivity Review. In: 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020), Xi'an, China, 25-30 Jul 2020, pp. 2053-2056. ISBN 9781450380164 (doi: 10.1145/3397271.3401267)

Narvala, H. , McDonald, G. and Ounis, I. (2020) Receptor: a Platform for Exploring Latent Relations in Sensitive Documents. In: 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020), Xi'an, China, 25-30 Jul 2020, pp. 2161-2164. ISBN 9781450380164 (doi: 10.1145/3397271.3401407)

2019

McDonald, G. , Macdonald, C. and Ounis, I. (2019) The FACTS of Technology-Assisted Sensitivity Review. Workshop on Fairness, Accountability, Confidentiality, Transparency, and Safety in Information Retrieval (FACTS-IR (SIGIR'19 Workshop)), Paris, France, 25 Jul 2019.

Mcdonald, G. , Macdonald, C. and Ounis, I. (2019) How Sensitivity Classification Effectiveness Impacts Reviewers in Technology-Assisted Sensitivity Review. In: ACM SIGIR Conference on Human Information Interaction & Retrieval (CHIIR), Glasgow, UK, 10-14 Mar 2019, pp. 337-341. ISBN 9781450360258 (doi: 10.1145/3295750.3298962)

2018

McDonald, G. , Macdonald, C. and Ounis, I. (2018) Active Learning Strategies for Technology Assisted Sensitivity Review. In: 40th European Conference on Information Retrieval (ECIR 2018), Grenoble, France, 25-29 Mar 2018, pp. 439-453. ISBN 9783319769400 (doi: 10.1007/978-3-319-76941-7_33)

McDonald, G. , Macdonald, C. and Ounis, I. (2018) Towards Maximising Openness in Digital Sensitivity Review using Reviewing Time Predictions. In: 40th European Conference on Information Retrieval (ECIR 2018), Grenoble, France, 25-29 Mar 2018, pp. 699-706. ISBN 9783319769400 (doi: 10.1007/978-3-319-76941-7_65)

2017

Mcdonald, G. , García-Pedrajas, N., Macdonald, C. and Ounis, I. (2017) A Study of SVM Kernel Functions for Sensitivity Classification Ensembles with POS Sequences. In: SIGIR 2017: The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Tokyo, Japan, 7-11 Aug 2017, pp. 1097-1100. ISBN 9781450350228 (doi: 10.1145/3077136.3080731)

McDonald, G. , Macdonald, C. and Ounis, I. (2017) Enhancing Sensitivity Classification with Semantic Features using Word Embeddings. In: 39th European Conference on Information Retrieval, Aberdeen, Scotland, 8-13 April 2017, pp. 450-463. (doi: 10.1007/978-3-319-56608-5_35)

This list was generated on Sat Nov 26 13:36:49 2022 GMT.
Number of items: 14.

Articles

McDonald, G. , Macdonald, C. and Ounis, I. (2022) Search results diversification for effective fair ranking in academic search. Information Retrieval Journal, 25(1), pp. 1-26. (doi: 10.1007/s10791-021-09399-z)

McDonald, G. , Macdonald, C. and Ounis, I. (2021) How the accuracy and confidence of sensitivity classification affects digital sensitivity review. ACM Transactions on Information Systems, 39(1), 4. (doi: 10.1145/3417334)

Conference or Workshop Item

McDonald, G. , Macdonald, C. and Ounis, I. (2019) The FACTS of Technology-Assisted Sensitivity Review. Workshop on Fairness, Accountability, Confidentiality, Transparency, and Safety in Information Retrieval (FACTS-IR (SIGIR'19 Workshop)), Paris, France, 25 Jul 2019.

Conference Proceedings

Narvala, H. , McDonald, G. and Ounis, I. (2022) Sensitivity Review of Large Collections by Identifying and Prioritising Coherent Documents Groups. In: Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM ’22), Atlanta, GA, USA, 17-21 October 2022, pp. 4931-4935. ISBN 9781450392365 (doi: 10.1145/3511808.3557182)

Narvala, H. , McDonald, G. and Ounis, I. (2022) The Role of Latent Semantic Categories and Clustering in Enhancing the Efficiency of Human Sensitivity Review. In: Seventh ACM SIGIR Conference on Human Information Interaction and Retrieval (ACM CHIIR 2022), Regensburg, Germany, 14-18 Mar 2022, pp. 56-66. ISBN 9781450391863 (doi: 10.1145/3498366.3505824)

Frayling, E., Macdonald, C. , McDonald, G. and Ounis, I. (2022) Using Entities in Knowledge Graph Hierarchies to Classify Sensitive Information. In: 13th International Conference of the CLEF Association (CLEF 2022), Bologna, Italy, 5-8 Sept 2022, pp. 125-132. ISBN 9783031136429 (doi: 10.1007/978-3-031-13643-6_10)

Narvala, H. , McDonald, G. and Ounis, I. (2021) RelDiff: Enriching Knowledge Graph Relation Representations for Sensitivity Classification. In: 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, 07-11 Nov 2021, pp. 3671-3681. ISBN 9781955917100

McDonald, G. , Macdonald, C. and Ounis, I. (2020) Active Learning Stopping Strategies for Technology-Assisted Sensitivity Review. In: 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020), Xi'an, China, 25-30 Jul 2020, pp. 2053-2056. ISBN 9781450380164 (doi: 10.1145/3397271.3401267)

Narvala, H. , McDonald, G. and Ounis, I. (2020) Receptor: a Platform for Exploring Latent Relations in Sensitive Documents. In: 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020), Xi'an, China, 25-30 Jul 2020, pp. 2161-2164. ISBN 9781450380164 (doi: 10.1145/3397271.3401407)

Mcdonald, G. , Macdonald, C. and Ounis, I. (2019) How Sensitivity Classification Effectiveness Impacts Reviewers in Technology-Assisted Sensitivity Review. In: ACM SIGIR Conference on Human Information Interaction & Retrieval (CHIIR), Glasgow, UK, 10-14 Mar 2019, pp. 337-341. ISBN 9781450360258 (doi: 10.1145/3295750.3298962)

McDonald, G. , Macdonald, C. and Ounis, I. (2018) Active Learning Strategies for Technology Assisted Sensitivity Review. In: 40th European Conference on Information Retrieval (ECIR 2018), Grenoble, France, 25-29 Mar 2018, pp. 439-453. ISBN 9783319769400 (doi: 10.1007/978-3-319-76941-7_33)

McDonald, G. , Macdonald, C. and Ounis, I. (2018) Towards Maximising Openness in Digital Sensitivity Review using Reviewing Time Predictions. In: 40th European Conference on Information Retrieval (ECIR 2018), Grenoble, France, 25-29 Mar 2018, pp. 699-706. ISBN 9783319769400 (doi: 10.1007/978-3-319-76941-7_65)

Mcdonald, G. , García-Pedrajas, N., Macdonald, C. and Ounis, I. (2017) A Study of SVM Kernel Functions for Sensitivity Classification Ensembles with POS Sequences. In: SIGIR 2017: The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Tokyo, Japan, 7-11 Aug 2017, pp. 1097-1100. ISBN 9781450350228 (doi: 10.1145/3077136.3080731)

McDonald, G. , Macdonald, C. and Ounis, I. (2017) Enhancing Sensitivity Classification with Semantic Features using Word Embeddings. In: 39th European Conference on Information Retrieval, Aberdeen, Scotland, 8-13 April 2017, pp. 450-463. (doi: 10.1007/978-3-319-56608-5_35)

This list was generated on Sat Nov 26 13:36:49 2022 GMT.

Supervision

  • Janich, Thomas Benedikt
    Fair Machine Learning for Search and Recommendation Systems
  • Narvala, Hitarth
    A System for Efficient yet Accurate Sensitivity Review: Leveraging Latent Relations in Documents to Maximise the Review Throughput