eprintid: 10192186 rev_number: 8 eprint_status: archive userid: 699 dir: disk0/10/19/21/86 datestamp: 2024-05-13 11:18:49 lastmod: 2025-01-22 07:10:06 status_changed: 2024-05-13 11:18:49 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Arbiv, Ruth C creators_name: Lovat, Laurence creators_name: Rosenfeld, Avi creators_name: Sarne, David title: Optimizing Decision Trees for Enhanced Human Comprehension ispublished: pub divisions: UCL divisions: B02 divisions: C10 divisions: D16 divisions: G88 note: This version is the author-accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: This paper studies a novel approach for training people to perform complex classification tasks using decision trees. The main objective of this study is to identify the most effective subset of rules for instructing users on how to excel in classification tasks themselves. The paper addresses the challenge of striking a balance between maximizing knowledge by incorporating numerous rules and the need to limit rules to prevent cognitive overload. To investigate this matter, a series of experiments were conducted, training users using decision trees to identify cases where cancer is suspected, and further testing is required. Notably, the study revealed a correlation between the decision tree characteristics and users’ comprehension levels. Building on these experimental outcomes, a machine learning model was developed to predict users’ comprehension levels based on different decision trees, thereby facilitating the selection of the most appropriate tree. To further assess the machine learning model’s performance, additional experiments were carried out using an alternative dataset focused on Crohn’s disease. The results demonstrated a significant enhancement in user understanding and classification performance. These findings emphasize the potential to improve human understanding and decision rule explainability by effectively modeling users’ comprehension. date: 2024-01-21 date_type: published publisher: Springer Nature Switzerland official_url: https://doi.org/10.1007/978-3-031-50396-2_21 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2248338 doi: 10.1007/978-3-031-50396-2_21 isbn_13: 9783031503955 lyricists_name: Lovat, Laurence lyricists_id: LBLOV52 actors_name: Lovat, Laurence actors_id: LBLOV52 actors_role: owner full_text_status: public pres_type: paper series: ECAI International Workshops publication: Communications in Computer and Information Science volume: 1947 place_of_pub: Cham, Switzerland pagerange: 366-381 event_title: Artificial Intelligence. ECAI 2023 International Workshops issn: 1865-0929 book_title: The Proceedings of the Artificial Intelligence. ECAI 2023 International Workshops editors_name: Nowaczyk, Slawomir editors_name: Biecek, Przemyslaw editors_name: Chung, Neo Christopher editors_name: Vallati, Mauro editors_name: Skruch, Pawel editors_name: Jaworek-Korjakowska, Joanna editors_name: Parkinson, Simon editors_name: Nikitas, Alexandros editors_name: Atzmüller, Martin editors_name: Kliegr, Tomás editors_name: Schmid, Ute editors_name: Bobek, Szymon editors_name: Lavrac, Nada editors_name: Peeters, Marieke editors_name: Dierendonck, Roland van editors_name: Robben, Saskia editors_name: Mercier-Laurent, Eunika editors_name: Kayakutlu, Gülgün editors_name: Owoc, Mieczyslaw Lech editors_name: Mason, Karl editors_name: Wahid, Abdul editors_name: Bruno, Pierangela editors_name: Calimeri, Francesco editors_name: Cauteruccio, Francesco editors_name: Terracina, Giorgio editors_name: Wolter, Diedrich editors_name: Leidner, Jochen L editors_name: Kohlhase, Michael editors_name: Dimitrova, Vania citation: Arbiv, Ruth C; Lovat, Laurence; Rosenfeld, Avi; Sarne, David; (2024) Optimizing Decision Trees for Enhanced Human Comprehension. In: Nowaczyk, Slawomir and Biecek, Przemyslaw and Chung, Neo Christopher and Vallati, Mauro and Skruch, Pawel and Jaworek-Korjakowska, Joanna and Parkinson, Simon and Nikitas, Alexandros and Atzmüller, Martin and Kliegr, Tomás and Schmid, Ute and Bobek, Szymon and Lavrac, Nada and Peeters, Marieke and Dierendonck, Roland van and Robben, Saskia and Mercier-Laurent, Eunika and Kayakutlu, Gülgün and Owoc, Mieczyslaw Lech and Mason, Karl and Wahid, Abdul and Bruno, Pierangela and Calimeri, Francesco and Cauteruccio, Francesco and Terracina, Giorgio and Wolter, Diedrich and Leidner, Jochen L and Kohlhase, Michael and Dimitrova, Vania, (eds.) The Proceedings of the Artificial Intelligence. ECAI 2023 International Workshops. (pp. pp. 366-381). Springer Nature Switzerland: Cham, Switzerland. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10192186/1/journal.pdf