Modeling and Understanding Human Routine Behavior

  title={Modeling and Understanding Human Routine Behavior},
  author={Nikola Banovic and Tofi Buzali and Fanny Chevalier and Jennifer Mankoff and Anind K. Dey},
  journal={Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems},
  • Nikola BanovicTofi Buzali A. Dey
  • Published 7 May 2016
  • Computer Science
  • Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems
Human routines are blueprints of behavior, which allow people to accomplish purposeful repetitive tasks at many levels, ranging from the structure of their day to how they drive through an intersection. People express their routines through actions that they perform in the particular situations that triggered those actions. An ability to model routines and understand the situations in which they are likely to occur could allow technology to help people improve their bad habits, inexpert… 

Figures and Tables from this paper

Leveraging Human Routine Models to Detect and Generate Human Behaviors

This work presents an approach that bypasses labeling each behavior instance that a person exhibits, and weakly label instances using people's demonstrated routine, which enables technology that can trigger interventions and help people reflect on their behaviors when those behaviors are likely to negatively impact them.

Method for Understanding Complex Human Routine Behaviors from Large Behavior Logs

This research model behaviors as sequences of actions people perform in specific situations and uses those computational models of routines together with different visualization tools to aid researchers and domain experts in exploring, making sense of, and generating new insights about human behavior in a principled way.

Human Behavior as a Process Model: Which Language to Use?

A set of key properties that a process modeling language needs to fulfill to capture human behavior are identified, which represent a valuable opportunity to monitor human-related processes.

Modelling Human Decision-making based on Aggregate Observation Data

Results are presented from a recent study where it is demonstrated how inference can be performed for RL models even when the observation data is significantly more coarse-grained, to solve the inverse reinforcement learning (IRL) problem using approximate Bayesian computation sped up with Bayesian optimization.

Theory-based habit modeling for enhancing behavior prediction in behavior change support systems

This paper proposes a method to enable intelligent systems to compute habit strength based on observable behavior and provides initial support for the theory-based approach of modeling user habits and encourages the use of habit computation to deliver personalized and adaptive interventions.

Understanding People’s Experience for Physical Activity Planning and Exploring the Impact of Historical Records on Plan Creation and Execution

Making and executing physical activity plans can help people improve their physical activity levels. However, little is known about how people make physical activity plans in everyday settings and

RuleSelector: Selecting Conditional Action Rules from User Behavior Patterns

This work designs and implements RuleSelector, the first interactive rule selection tool to allow smartphone users to browse, modify, and select action rules from a small set of summarized rules presented to the user.

Bayesian method for intent prediction in pervasive computing environments

The popular intelligent algorithms used in recent HCI researches are summarized, the difference between these methods are discussed, and the methods of user modelling and the Bayesian method are illustrated using some works from the authors' laboratory.

Predicting Consumption Patterns with Repeated and Novel Events

This work finds that widely-used matrix factorization methods are limited in their ability to capture important details in historical behavior, resulting in relatively low predictive accuracy for these types of problems, and proposes an interpretable and scalable mixture model framework that balances individual preferences in terms of exploration and exploitation.

Computational Model of the Transition from Novice to Expert Interaction Techniques

A dedicated model is introduced, Transition, combining five cognitive mechanisms: implicit and explicit learning, decay, planning and perseveration, which outperforms the three benchmark models both in terms of model fitting and model simulation.



How routine learners can support family coordination

A vision of how simple sensing technology could capture and model idiosyncratic routines, enabling applications to solve many real world problems is offered, to identify how a simple routine learner can demonstrate this in support of family coordination.

Learning patterns of pick-ups and drop-offs to support busy family coordination

This work demonstrates the feasibility of learning family routines using mobile phone GPS, and discusses how these routine models give digital calendars, reminder and location systems new capabilities to help prevent breakdowns, and improve family life.

Reconceptualizing Organizational Routines as a Source of Flexibility and Change

In this paper, we challenge the traditional understanding of organizational routines as creating inertia in organizations. We adapt Latour's distinction between ostensive and performative to build a

Eigenbehaviors: identifying structure in routine

This work identifies the structure inherent in daily behavior with models that can accurately analyze, predict, and cluster multimodal data from individuals and communities within the social network of a population with the potential for this dimensionality reduction technique to infer community affiliations within the subjects’ social network.

Navigate like a cabbie: probabilistic reasoning from observed context-aware behavior

We present PROCAB, an efficient method for Probabilistically Reasoning from Observed Context-Aware Behavior. It models the context-dependent utilities and underlying reasons that people take

Predestination: Inferring Destinations from Partial Trajectories

A method called Predestination is described that uses a history of a driver's destinations, along with data about driving behaviors, to predict where a driver is going as a trip progresses, to produce a probabilistic map of destinations.

Learning Probabilistic Hierarchical Task Networks as Probabilistic Context-Free Grammars to Capture User Preferences

We introduce an algorithm to automatically learn probabilistic hierarchical task networks (pHTNs) that capture a user's preferences on plans by observing only the user's behavior. HTNs are a common

Temporal task footprinting: identifying routine tasks by their temporal patterns

Experimental evaluations showed that temporal task footprints of application windows, email and document usage outperform decision tree and SVMs in recognizing the subjects' tasks.

Discovering hidden time patterns in behavior: T-patterns and their detection

  • M. Magnússon
  • Computer Science
    Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc
  • 2000
This article deals with the definition and detection of particular kinds of temporal patterns in behavior, which are sometimes obvious or well known, but other times difficult to detect, either