Takeshi Kurashima's Website

Takeshi KURASHIMA

I am a Researcher at NTT Human Informatics Laboratories, NTT Corporation. My research focuses on mining and modeling human activities. I was a Visiting Scholar at Computer Science, Stanford University. I worked with Jure Leskovec and was part of SNAP, the InfoLab.

DBLP

Google Scholar

What's new

March 2025: Our paper "Estimating Impact of Behavior Change Messages Using Large Language Models" has been accepted at PAKDD 2025 (Special Session).
January 2025: Our paper "The Role of Initial Acceptance Attitudes Toward AI Decisions in Algorithmic Recourse" has been accepted at CHI 2025.
December 2024: Our paper "A Continuous-time Tractable Model for Present-biased Agents" has been accepted at AAAI 2025.
May 2024: Our paper "Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspective" has been accepted at IJCAI 2024 Special Track on Human-Centered AI.
December 2023: Our paper "Analytically Tractable Models for Decision Making under Present Bias" has been accepted at AAAI 2024. This paper was selected as oral presentation [120 / 9862 = 1.2%].
June 2023: Our paper "Personal History Affects Reference Points: A Case Study of Codeforces" won the Best Paper Award (Outstanding User Modeling) at ICWSM 2023!

Conference Papers

- Estimating Impact of Behavior Change Messages Using Large Language Models

Takuya Okada, Yoshiaki Takimoto, Takeshi Kurashima, and Hiroyuki Toda
The 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2025), Special Session, pp.*-*, June 2025 [acceptance rate: * / * = *%]

- The Role of Initial Acceptance Attitudes Toward AI Decisions in Algorithmic Recourse

Tomu Tominaga, Naomi Yamashita, and Takeshi Kurashima
The 2025 CHI Conference on Human Factors in Computing Systems (CHI 2025), No.260, pp.1-20, May 2025 [acceptance rate: 24.9%]

- A Continuous-time Tractable Model for Present-biased Agents

Yasunori Akagi, Hideaki Kim, and Takeshi KurashimaThe 39th AAAI Conference on Artificial Intelligence (AAAI 2025), pp.13510-13519, February 2025 [acceptance rate: 3032 / 12957 = 23.4%]

- Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspective

Tomu Tominaga, Naomi Yamashita, and Takeshi Kurashima
The 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), Special Track on Human-Centered AI, pp.7913-7921, August 2024 [acceptance rate: 11 / 199 = 5.5%]

- Analytically Tractable Models for Decision Making under Present Bias

Yasunori Akagi, Naoki Marumo, and Takeshi KurashimaThe 38th AAAI Conference on Artificial Intelligence (AAAI 2024), pp.9441-9450, February 2024
[acceptance rate: 2342 / 9862 = 23.8%, selected as oral presentation: 120 / 9862 = 1.2%]

- Inverse Problem of Censored Markov Chain: Estimating Markov Chain Parameters from Censored Transition Data

Masahiro Kohjime, Takeshi Kurashima, and Hiroyuki TodaThe 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2023), pp.297-308, May 2023 [acceptance rate: 143 / 869 = 16.5%]

- Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm

Yasunori Akagi, Naoki Marumo, Hideaki Kim, Takeshi Kurashima, and Hiroyuki TodaThe 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021) [acceptance rate: 2344 / 9122 = 25.7%]

- Price and Time Optimization for Utility-Aware Taxi Dispatching

Yuya Hikima, Masahiro Kohjima, Yasunori Akagi, Takeshi Kurashima, and Hiroyuki TodaThe 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI 2021) , pp.370-381, [acceptance rate: ( 98 regular + 30 short ) / 408 = 31.4 %]

- Effects of Intervening Backwards from Goals to Improve Sleep Habits

Masami Takahashi, Masahiro Kohjima, Ryo Hashimoto, Asuka Miyake, Takeshi Kurashima, and Hiroyuki TodaACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2021), pp.74-75 [poster]

- Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes

Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Hiroyuki Toda, Takeshi Kurashima, and Hisashi KashimaACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2021) , pp.1276-1286, August 2021 [acceptance rate: 238 / 1541 = 15.4%]

- Effects of Personal Characteristics on Temporal Response Patterns in Ecological Momentary Assessments

Tomu Tominaga, Shuhei Yamamoto, Takeshi Kurashima, and Hiroyuki TodaThe 18th IFIP TC13 International Conference on Human Computer Interaction (INTERACT 2021) , pp.3-22, August 2021 [acceptance rate: 29%]

- Integrated Optimization of Bipartite Matching and Its Stochastic Behavior: New Formulation and Approximation Algorithm via Min-cost Flow Optimization

Yuya Hikima, Yasunori Akagi, Hideaki Kim, Masahiro Kohjima, Takeshi Kurashima, and Hiroyuki TodaThe 35th AAAI Conference on Artificial Intelligence (AAAI 2021), pp.3796-3805, February 2021 [acceptance rate: 1692 / 7911 = 21.4%]

- Can Reinforcement Learning Lead to Healthy Life?: Simulation Study Based on User Activity Logs

Masami Takahashi, Masahiro Kohjima, Takeshi Kurashima, and Hiroyuki TodaInternational Conference on Pattern Recognition (ICPR 2020), pp.4865-4872, January 2021

- Learning with Labeled and Unlabeled Multi-Step Transition Data for Recovering Markov Chain from Incomplete Transition Data

Masahiro Kohjima, Takeshi Kurashima, and Hiroyuki TodaThe 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI 2020) , pp.2412-2419, July 2020 [acceptance rate: 592 / 4717 = 12.6%]

- Identifying Near-Miss Traffic Incidents in Event Recorder Data

Shuhei Yamamoto, Takeshi Kurashima, and Hiroyuki TodaThe 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2020), pp.717-728, May 2020 [acceptance rate: * / 628 = 21%]

- Exact and Efficient Inference for Collective Flow Diffusion Model via Minimum Convex Cost Flow Algorithm

Yasunori Akagi, Takuya Nishimura, Yusuke Tanaka, Takeshi Kurashima, and Hiroyuki TodaThe 34th AAAI Conference on Artificial Intelligence (AAAI 2020), pp.3163-3170, February 2020 [acceptance rate: 1591 / 7737 = 20.6%]

- Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs

Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi, and Hiroyuki TodaThe 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019), pp.3000–3010, December 2019 [acceptance rate: 1428 / 6743 = 21.2%]

- Coordinated Traffic Signal Control via Bayesian Optimization for Hierarchical Conditional Spaces

Hidetaka Ito, Kyota Tsutsumida, Tatsushi Matsubayashi, Takeshi Kurashima, and Hiroyuki TodaThe 2019 Winter Simulation Conference (WSC 2019), December 2019

- Predicting Traffic Accidents with Event Recorder Data

Yoshiaki Takimoto, Yusuke Tanaka, Takeshi Kurashima, Shuhei Yamamoto, Maya Okawa, and Hiroyuki TodaThe 3rd ACM SIGSPATIAL International Workshop on Prediction of Human Mobility (PredictGIS), pp.11-14, November 2019

- Identifying Self-changeable Actions toward Regulating Rhythm of Daily Life

Masami Takahashi, Masahiro Kohjima, Takeshi Kurashima, Tatsushi Matsubayashi, and Hiroyuki TodaACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2019), pp.218-221, September 2019 [poster]

- Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information

Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda, and Naonori UedaACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019), pp.373-383, August 2019 [acceptance rate: 174 / 1179 = 14.8%]

- Refining Coarse-grained Spatial Data using Auxiliary Spatial Data Sets with Various Granularities

Yusuke Tanaka, Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Kurashima, Maya Okawa, and Hiroyuki TodaThe 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), pp.5091-5099, January 2019 [acceptance rate: 1150 / 7095 = 16.2%]

- A Fast and Accurate Method for Estimating People Flow from Spatiotemporal Population Data

Yasunori Akagi, Takuya Nishimura, Takeshi Kurashima, and Hiroyuki TodaInternational Joint Conference on Artificial Intelligence and European Conference on Artificial Intelligence (IJCAI-ECAI 2018), pp.3293-3300, July 2018

- Estimating Latent People Flow without Tracking Individuals

Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima, Hiroyuki Toda, and Naonori UedaInternational Joint Conference on Artificial Intelligence and European Conference on Artificial Intelligence (IJCAI-ECAI 2018), pp.3556-3563, July 2018 [acceptance rate: 710 / 3470 = 20.5%]

- Modeling Interdependent and Periodic Real-World Action Sequences

Takeshi Kurashima, Tim Althoff, and Jure LeskovecThe Web Conference (WWW 2018), pp.803-812, April 2018 [acceptance rate: 171 / 1155 = 14.8%]

- Inferring Latent Triggers of Purchases with Consideration of Social Effects and Media Advertisement

Yusuke Tanaka, Takeshi Kurashima, Yasuhiro Fujiwara, Tomoharu Iwata, and Hiroshi SawadaACM International Conference on Web Search and Data Mining (WSDM 2016), pp.543-552, February 2016 [acceptance rate: 18.2%]

- Probabilistic Identification of Visited Point-of-Interest for Personalized Automatic Check-in

Kyosuke Nishida, Hiroyuki Toda, Takeshi Kurashima, and Yoshihiko SuharaACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014), pp.631–642, September 2014 [acceptance rate: 20.7%]

- Probabilistic Latent Network Visualization: Inferring and Embedding Diffusion Networks

Takeshi Kurashima, Tomoharu Iwata, Noriko Takaya, and Hiroshi SawadaACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2014), pp.1236–1245, August 2014 [acceptance rate: 151 / 1036 = 14.6%]

- A Probabilistic Behavior Model for Discovering Unrecognized Knowledge

Takeshi Kurashima, Tomoharu Iwata, Noriko Takaya, and Hiroshi SawadaIEEE International Conference on Data Mining (ICDM 2013), pp.1097–1102, December 2013 [acceptance rate: 19.7%]

- Geo Topic Model: Joint Modeling of User’s Activity Area and Interests for Location Recommendation

Takeshi Kurashima, Tomoharu Iwata, Takahide Hoshide, Noriko Takaya, and Ko FujimuraACM International Conference on Web Search and Data Mining (WSDM 2013), pp.375–384, February 2013 [acceptance rate: 73 / 387 = 18.9%]

- Travel Route Recommendation using Geotags in Photo Sharing Sites

Takeshi Kurashima, Tomoharu Iwata, Go Irie, and Ko FujimuraACM International Conference on Information and Knowledge Management (CIKM 2010), pp.579–588, October 2010 [acceptance rate: 127 / 945 = 13.4%]

- Discovering Association Rules on Experiences from Large-Scale Blog Entries

Takeshi Kurashima, Ko Fujimura, and Hidenori OkudaEuropean Conference on Information Retrieval (ECIR 2009), pp.546–553, April 2009

- Ranking Entities using Comparative Relations

Takeshi Kurashima, Katsuji Bessho, Hiroyuki Toda, Toshio Uchiyama, and Ryoji KataokaInternational Conference on Database and Expert Systems Applications (DEXA 2008), pp.124–133, September 2008

- Mining and Visualizing Local Experiences from Blog Entries

Takeshi Kurashima, Taro Tezuka, and Katsumi TanakaInternational Conference on Database and Expert Systems Applications (DEXA 2006), pp.213–222, September 2006 [acceptance rate: 90 / 388 = 23.2%]

- Toward Tighter Integration of Web Search with a Geographic Information System

Taro Tezuka, Takeshi Kurashima, and Katsumi TanakaInternational Conference on World Wide Web (WWW 2006), pp.277–286, May 2006 [acceptance rate: 84 / 697 = 12.1%]

- Blog Map of Experiences: Extracting and Geographically Mapping Visitor Experiences from Urban Blogs

Takeshi Kurashima, Taro Tezuka, and Katsumi TanakaInternational Conference on Web Information Systems Engineering (WISE 2005), pp.496–503, November 2005 [acceptance rate: (30 regular + 24 short ) / 259 = 20.8%]

Journals

- Estimating Present Bias using Behavior History

Yasunori Akagi, Shuhei Yamamoto, Tomu Tominaga, and Takeshi Kurashima
IEICE Transactions on Information and Systems, Vol. *-*, No.*, pp.*-*, 2025

- Evaluation of Incentives for Achieving Effective Health Promotion Messages

Yoshiaki Takimoto, Hideaki Kim, Nozomi Kobayashi, and Takeshi KurashimaIEICE Transactions on Information and Systems, Vol.J *-*, No.*, pp.*–*, May 2025 (in Japanese)

- Investigation of Optimal Loss-Framed Incentive Strategies Based on a Scenario Experiment to Promote Health Behavior

Yuka Nishida, Hideaki Kim, and Takeshi KurashimaIPSJ Transactions on Databases (TOD), Vol.18, No.2, pp.1–7, April 2025 (in Japanese)

- Personal History Affects Reference Points: A Case Study of Codeforces

Takeshi Kurashima, Tomoharu Iwata, Tomu Tominaga, Shuhei Yamamoto, Hiroyuki Toda, and Kazuhisa TakemuraThe 17th International Conference on Web and Social Media (ICWSM 2023) , Vol.17, No.8, pp.507-518, [acceptance rate: 84 / 444 =18.9%]
👑 Best Paper Award (Outstanding User Modeling Paper)

- Understanding How Personal Characteristics Affect Temporal Response Patterns in Experience Sampling Method: A Case Study of StudentLife Dataset

Tomu Tominaga, Shuhei Yamamoto, Takeshi Kurashima, and Hiroyuki TodaIPSJ Journal, Vol.64, No.2, pp.336-351, February 2023 (in Japanese)

- Price and Time Proposal Optimization for Ride-Hailing Services Based on Individual Utilities

Yuya Hikima, Yasunori Akagi, Masahiro Kohjima, Takeshi Kurashima, and Hiroyuki TodaTransactions of the Japanese Society for Artificial Intelligence, Vol.38, No.1, pp.C-M13_1, January 2023

- MAP Inference Algorithms without Approximation for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm

Yasunori Akagi, Naoki Marumo, Hideaki Kim, Takeshi Kurashima, and Hiroyuki TodaMachine Learning, Vol. 112, No. 1, pp.99-129, January 2023

- Context-aware Spatio-temporal Event Prediction via Convolutional Hawkes Processes

Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, and Hisashi KashimaMachine Learning, Vol. 111, No.8, pp.2929-2950, March 2022

- Classifying Near-Miss Traffic Incidents through Video, Sensor, and Object Features

Shuhei Yamamoto, Takeshi Kurashima, and Hiroyuki TodaIEICE Transactions on Information and Systems, Vol. E105-D, No.2, pp.377-386, Feb. 2022

- Deep Mixture Point Processes: Spatio-temporal Event Prediction with External Factor

Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda, Naonori Ueda, and Hisashi KashimaJournal of Japanese Society for Artificial Intelligence, Vol.36, No.5, p.C-L37_1-10, September 2021 (in Japanese)

- Time-delayed Collective Flow Diffusion Models for Inferring Latent People Flow from Aggregated Data at Limited Locations

Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima, Hiroyuki Toda, Naonori Ueda, and Toshiyuki TanakaArtificial Intelligence, Vol. 292, March 2021, 103430

- Predicting Traffic Accidents with Dashboard Cameras

Yoshiaki Takimoto, Yusuke Tanaka, Takeshi Kurashima, Shuhei Yamamoto, Maya Okawa, and Hiroyuki TodaIPSJ Transactions on Databases (TOD), Vol.14, No.1, pp.1-7, January 2021 (in Japanese)

- Pattern Analysis of Daily Activity and Intervention Acceptability Using Nonnegative Multiple Tensor Factorization with Convolutive Transformation Matrix

Masahiro Kohjima, Masami Takahashi, Takeshi Kurashima, Tatsushi Matsubayashi, and Hiroyuki TodaIEICE Transactions on Information and Systems, Vol. 103, No.10, pp.664-675, October 2020 (in Japanese)

- Domain Adaptation based on Adversarial Learning for Detection and Classification of Near-miss Incident from Dashcam Data

Yoshiaki Takimoto, Shuhei Yamamoto, Tatsushi Matsubayashi, Takeshi Kurashima, Hiroyuki TodaIPSJ Transactions on Databases (TOD), Vol.13, No.3, pp.1-9, July 2020 (in Japanese)

- Marked Temporal Point Processes for Trip Demand Prediction in Bike Sharing Systems

Maya Okawa, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, and Tomohiro YamadaIEICE Transactions on Information and Systems, Vol. E102.D (9), pp.1635-1643, June 2019

- People Flow Estimation from Spatiotemporal Population Data that Considers the Characteristics of Human Movement

Yasunori Akagi, Takuya Nishimura, Takeshi Kurashima, and Hiroyuki TodaDBSJ Journal, Vol.17-j, No.9, March 2019 (in Japanese)

- Identifying Latent Triggers of Purchases with Consideration of Social Effects and Media Advertisements

Yusuke Tanaka, Takeshi Kurashima, Yasuhiro Fujiwara, Tomoharu Iwata, and Hiroshi SawadaIPSJ Journal, Vol.58, No.2, pp.580-593, Feburary 2017 (in Japanese)

- User Status Estimation Using E-Commerce Site’s Access Logs

Yusuke Kumagae, Takeshi Kurashima, Noriko Takaya, and Tadasu UchiyamaDBSJ Journal, Vol.12, No.1, pp.67–72, June 2013 (in Japanese)

- Joint Modeling of User’s Activity Area and Interests for Local Recommendation

Takeshi Kurashima, Tomoharu Iwata, Takahide Hoshide, Noriko Takaya, and Ko FujimuraIPSJ Transactions on Databases (TOD), Vol.6, No.2, pp.30–41, March 2013 (in Japanese)

- Travel Route Recommendation using Geotagged Photos

Takeshi Kurashima, Tomoharu Iwata, Go Irie and Ko FujimuraKnowledge and Information Systems (KAIS journal), Vol.37, No.1, pp.37–60, October 2012

- Estimating Method on Choosing the Item in E-Commerce

Kenji Esaki, Takeshi Kurashima, Yusuke Ichikawa, Noriko Takaya, and Tadasu UchiyamaDBSJ Journal, Vol.11, No.1, pp.13–18, June 2012 (in Japanese)

- Mining Experiences from Large-Scale Texts

Takeshi Kurashima, Ko Fujimura, and Hidenori OkudaIEICE Transactions on Information and Systems, Vol.J 92-D, No.3, pp.301–310, March 2009 (in Japanese)

- Ranking Method using Comparative Relations

Takeshi Kurashima, Katsuji Bessho, Hiroyuki Toda, Toshio Uchiyama, Ryoji Kataoka, and Masahiro OkuDBSJ Letters Vol.6, No.1, pp.5-8, 2007 (in Japanese)

Program Committee Member

- AAAI 2020-2025 - AAAI Conference on Artificial Intelligence 2020, 2021, 2022, 2023, 2024, 2025
- NeurIPS 2020-2024 - The Annual Conference on Neural Information Processing Systems, 2020, 2021, 2022, 2023, 2024 (Reviewer)
- ICML 2021-2025 - The International Conference on Machine Learning, 2021, 2022, 2023, 2024, 2025
- IJCAI 2018-2020 - International Joint Conference on Artificial Intelligence 2018, 2019, 2020

IJCAI-ECAI 2018 Distinguished PC and SPC Members, 2018

- ECML-PKDD 2020 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020

Biography

- Jul. 2021 - Present: Researcher at NTT Human Informatics Laboratories, NTT Corporation
- Jul. 2012 - Jun. 2021: Researcher at NTT Service Evolution Laboratories, NTT Corporation
- Apr. 2016 - Apr.2017: Visiting Scholar at Computer Science, Stanford University ( Sponsor: Jure Leskovec )
- Oct. 2011 - Sep. 2014: Ph.D. in Informatics, Kyoto University, Japan ( Supervisor: Katsumi Tanaka )
- Apr. 2006 - Jun. 2012: Researcher at NTT Cyber Solutions Laboratories, NTT Corporation
- Apr. 2004 - Mar. 2006: Master of Informatics, Kyoto University, Japan
- Apr. 2000 - Mar. 2004: Bachelor of Engineering, Doshisha University, Japan

Contact

- E-mail: [my first name] . [my last name] [at] ntt.com
- Address: 1-1 Hikarinooka, Yokosuka, Kanagawa, 239-0847, Japan

Last updated: May 2025

Google Sites

Report abuse