An official website of the United States government
Identifying instances when a user will not able to attend to an incoming message and constructing an auto-response with relevant contextual information may help reduce social pressures to immediately respond that many users face. Mobile messaging behavior often varies from one person to another. As a result, compared to a generic model considering profiles of several users, a personalized model can capture a user's messaging behavior more accurately to predict their inattentive states. However, creating accurate personalized models requires a non-trivial amount of individual data, which is often not available for new users. In this work, we investigate a weighted hybrid approach to model users' attention to messaging. Through dynamic performance-based weighting, we combine the predictions of three types of models, a general model, a group model and a personalized model to create an approach which can work through the lack of initial data while adapting to the user's behavior. We present the details of our modeling approach and the evaluation of the model with over three weeks of data from 274 users. Our results highlight the value of hybrid weighted modeling to predict when a user cannot attend to their messages.
more »
« less
Are You There?: Identifying Unavailability in Mobile Messaging
Delays in response to mobile messages can cause negative emotions in message senders and can affect an individual's social relationships. Recipients, too, feel a pressure to respond even during inopportune moments. A messaging assistant which could respond with relevant contextual information on behalf of individuals while they are unavailable might reduce the pressure to respond immediately and help put the sender at ease. By modelling attentiveness to messaging, we aim to (1) predict instances when a user is not able to attend to an incoming message within reasonable time and (2) identify what contextual factors can explain the user's attentiveness---or lack thereof---to messaging. In this work, we investigate two approaches to modelling attentiveness: a general approach in which data from a group of users is combined to form a single model for all users; and a personalized approach, in which an individual model is created for each user. Evaluating both models, we observed that on average, with just seven days of training data, the personalized model can outperform the generalized model in terms of both accuracy and F-measure for predicting inattentiveness. Further, we observed that in majority of cases, the messaging patterns identified by the attentiveness models varied widely across users. For example, the top feature in the generalized model appeared in the top five features for only 41% of the individual personalized models.
more »
« less
- PAR ID:
- 10105768
- Date Published:
- Journal Name:
- Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Plausible deniability in cryptography allows users to deny their participation in a particular communication or the contents of their messages, thereby ensuring privacy. Popular end-to-end encrypted messaging apps employ the Signal protocol, which incorporates message deniability. However, their current user interfaces only allow access to the blunt tool of message deletion. Denying a message requires users to claim that the counterpart in their conversation has the technical sophistication to forge a message when no usable message forgery tools are available. We evaluate a step towards bridging this gap in the form of a new transcript-editing feature implemented within the Signal app which allows each user to maintain an independent, locally-editable transcript of their conversation. We gave users hands-on experience with this app in the context of resolving a social dispute, and measured their ability to understand its implications both technically and ethically. Users find our interface intuitive and can reason about deniability, but are divided by which circumstances for which deniability is appropriate or desirable. We recommend users be given transparent access to choose when their conversations are deniable versus non-repudiable, instead of the status quo of somewhere-in-between. Our study introduces a novel approach by providing hands-on experience and evaluating its usability. This method offers insights into practical deniability implementation and lays the groundwork for future research.more » « less
-
Private messaging platforms provide strong protection against platform eavesdropping, but malicious users can use privacy as cover for spreading abuse and misinformation. In an attempt to identify the sources of misinformation on private platforms, researchers have proposed mechanisms to trace back the source of a user-reported message (CCS '19,'21). Unfortunately, the threat model considered by initial proposals allowed a single user to compromise the privacy of another user whose legitimate content the reporting user did not like. More recent work has attempted to mitigate this side effect by requiring a threshold number of users to report a message before its origins can be identified (NDSS '22). However, the state of the art scheme requires the introduction of new probabilistic data structures and only achieves a fuzzy threshold guarantee. Moreover, false positives, where the source of an unreported message is identified, are possible. This paper introduces a new threshold source tracking technique that allows a private messaging platform, with the cooperation of a third-party moderator, to operate a threshold reporting scheme with exact thresholds and no false positives. Unlike prior work, our techniques require no modification of the message delivery process for a standard source tracking scheme, affecting only the abuse reporting procedure, and do not require tuning of probabilistic data structures.more » « less
-
Problem definition: We seek to provide an interpretable framework for segmenting users in a population for personalized decision making. Methodology/results: We propose a general methodology, market segmentation trees (MSTs), for learning market segmentations explicitly driven by identifying differences in user response patterns. To demonstrate the versatility of our methodology, we design two new specialized MST algorithms: (i) choice model trees (CMTs), which can be used to predict a user’s choice amongst multiple options, and (ii) isotonic regression trees (IRTs), which can be used to solve the bid landscape forecasting problem. We provide a theoretical analysis of the asymptotic running times of our algorithmic methods, which validates their computational tractability on large data sets. We also provide a customizable, open-source code base for training MSTs in Python that uses several strategies for scalability, including parallel processing and warm starts. Finally, we assess the practical performance of MSTs on several synthetic and real-world data sets, showing that our method reliably finds market segmentations that accurately model response behavior. Managerial implications: The standard approach to conduct market segmentation for personalized decision making is to first perform market segmentation by clustering users according to similarities in their contextual features and then fit a “response model” to each segment to model how users respond to decisions. However, this approach may not be ideal if the contextual features prominent in distinguishing clusters are not key drivers of response behavior. Our approach addresses this issue by integrating market segmentation and response modeling, which consistently leads to improvements in response prediction accuracy, thereby aiding personalization. We find that such an integrated approach can be computationally tractable and effective even on large-scale data sets. Moreover, MSTs are interpretable because the market segments can easily be described by a decision tree and often require only a fraction of the number of market segments generated by traditional approaches. Disclaimer: This work was done prior to Ryan McNellis joining Amazon. Funding: This work was supported by the National Science Foundation [Grants CMMI-1763000 and CMMI-1944428]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2023.1195 .more » « less
-
Personalized recommendation based on multi-arm bandit (MAB) algorithms has shown to lead to high utility and efficiency as it can dynamically adapt the recommendation strategy based on feedback. However, unfairness could incur in personalized recommendation. In this paper, we study how to achieve user-side fairness in personalized recommendation. We formulate our fair personalized recommendation as a modified contextual bandit and focus on achieving fairness on the individual whom is being recommended an item as opposed to achieving fairness on the items that are being recommended. We introduce and define a metric that captures the fairness in terms of rewards received for both the privileged and protected groups. We develop a fair contextual bandit algorithm, Fair-LinUCB, that improves upon the traditional LinUCB algorithm to achieve group-level fairness of users. Our algorithm detects and monitors unfairness while it learns to recommend personalized videos to students to achieve high efficiency. We provide a theoretical regret analysis and show that our algorithm has a slightly higher regret bound than LinUCB. We conduct numerous experimental evaluations to compare the performances of our fair contextual bandit to that of LinUCB and show that our approach achieves group-level fairness while maintaining a high utility.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3290607.3312893
