SCI IC PFP Group

Group

Related publications (97)

Recommender systems (RSs), as used by Netflix, YouTube, or Amazon, are one of the most compelling success stories of AI. Enduring research activity in this area has led to a continuous improvement of recommendation techniques over the years, and today's RSs are indeed often capable to make astonishingly good suggestions. With countless papers being published on the topic each year, one might think the recommendation problem is almost solved. In reality, however, the large majority of published works focuses on algorithmic improvements and relies on data-based evaluation procedures which may sometimes tell us little regarding the effects new algorithms will have in practice. This special issue contains a set of papers which address some of the open challenges and frontiers in RSs research: (i) building interactive and conversational solutions, (ii) understanding recommender systems as socio-technical systems with longitudinal dynamics, (iii) avoiding abstraction traps, and (iv) finding better ways of assessing the impact and value of recommender systems without field tests.

AMER ASSOC ARTIFICIAL INTELL2022

Key Qualities of Conversational Chatbots - the PEACE Model

Pearl Pu Faltings, Ekaterina Svikhnushina

Open-domain chatbots engage in natural conversations with the user to socialize and establish bonds. However, designing and developing an effective open-domain chatbot is challenging. It is unclear what qualities of such chatbots most correspond to users' expectations. Even though existing work has considered a wide range of aspects, some key components are still missing. More importantly, the consistency and validity of the combined criteria have not been tested. In this paper, we describe a large-scale survey using a consolidated model to elicit users' preferences, expectations, and concerns. We apply structural equation modeling methods to further validate the data collected from the user survey. The outcome supports the consistency, validity, and reliability of the model, which we call PEACE (Politeness, Entertainment, Attentive Curiosity, and Empathy). PEACE, therefore, defines the key determinants most predictive of user acceptance. This has allowed us to develop a set of implications useful for the development of compelling open-domain chatbots.

ASSOC COMPUTING MACHINERY2021

User Expectations of Conversational Chatbots Based on Online Reviews

Alexandru Placinta, Pearl Pu Faltings, Ekaterina Svikhnushina

Open-domain chatbots that can engage in a conversation on any topic received significant attention in the last several years, which opened opportunities for studying user interaction with them. Drawing from reviews of chatbots posted on Google Play, we explore user experience and expectations of these agents in a mixed-method study. Results of statistical analysis reveal which social qualities of chatbots are the most significant for user satisfaction. Further, we employ natural language processing and qualitative methods to identify how users wish their chatbots to evolve in the future. While currently users mostly value the entertaining component of their experience, their expectations call for more human-like behavior of chatbots. The most prominent expectations include chatbots' abilities to treat and express emotions and be more attentive to the user. Based on these findings, we conclude with design implications, discussing the directions for developing social skills of open-domain chatbots.

ASSOC COMPUTING MACHINERY2021

The origins of modern recommender systems date back to the early 1990s when they were mainly applied experimentally to personal email and information filtering. Today, 30 years later, personalized recommendations are ubiquitous and research in this highly successful application area of AI is flourishing more than ever. Much of the research in the last decades was fueled by advances in machine learning technology. However, building a successful recommender system requires more than a clever general-purpose algorithm. It requires an indepth understanding of the specifics of the application environment and the expected effects of the system on its users. Ultimately, making recommendations is a human-computer interaction problem, where a computerized system supports users in information search or decision-making contexts. This special issue contains a selection of papers reflecting this multi-faceted nature of the problem and puts open research challenges in recommender systems to the forefront. It features articles on the latest learning technology, reflects on the humancomputer interaction aspects, reports on the use of recommender systems in practice, and it finally critically discusses our research methodology.

AMER ASSOC ARTIFICIAL INTELL2021

Understanding intergenerational fitness tracking practices: 12 suggestions for design

Pearl Pu Faltings

The paper presents a qualitative study to explore the use of fitness trackers and their social functions in intergenerational settings. The study covered three phases of semi-structured interviews with older and younger adults during individual and intergenerational use of the fitness trackers. The study revealed comparability as common fitness practice for older adults. The findings show that intergenerational fitness tracking practices can increase in-person meetings and daily discourses and thus enhance family social bonds. An unexpected benefit of this practice is its ability to help older adults overcome technology barriers related to the use of fitness trackers. Overall speaking, families whose intergenerational members already enjoy a strong relationship are likely to gain the most from such practices. Many challenges remain especially concerning the motivation and involvement of younger partners and the user experience design aspect of such digital programs. For this purpose, we have developed some recommendations for the future development and deployment of intergenerational fitness tracking systems to stimulate interactions between younger and older family members and thus to promote their physical and emotional well-being.

SPRINGERNATURE2021

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Junze Li, Pearl Pu Faltings, Yubo Xie

Humor recognition has been widely studied as a text classification problem using data-driven approaches. However, most existing work does not examine the actual joke mechanism to understand humor. We break down any joke into two distinct components: the set-up and the punchline, and further explore the special relationship between them. Inspired by the incongruity theory of humor, we model the setup as the part developing semantic uncertainty, and the punchline disrupting audience expectations. With increasingly powerful language models, we were able to feed the set-up along with the punchline into the GPT-2 language model, and calculate the uncertainty and surprisal values of the jokes. By conducting experiments on the SemEval 2021 Task 7 dataset, we found that these two features have better capabilities of telling jokes from non-jokes, compared with existing baselines.

ASSOC COMPUTATIONAL LINGUISTICS-ACL2021

Identifying a Motivational Profile for Older Adults Towards Increased Physical Activity

Yuan Lu, Pearl Pu Faltings

Personalizing behavior change (BC) strategies to motivate increased physical activity is especially important for the diverse older adult population. However, there is a lack of knowledge about how to profile older users to most effectively personalize BC solutions. Self-awareness and social awareness are BC strategies commonly used in commercially available applications to promote physical activities. Through a randomized controlled trial (N = 53), we studied the effect of some personal factors on the physical activity of older adults under these two strategies. For this purpose, each BC strategy was implemented in a mobile application. Based on the statistical analysis of the measured step data and the collected questionnaire data, we identified a list of personal factors to personalize each BC strategy towards improved physical activity. Hereby we suggest how to create effective motivational profiles and provide design recommendations to personalize these BC strategies toward increased physical activity for older users.

2021

, ,

Geo-replicated data platforms are the backbone of several large-scale online services. Transactional Causal Consistency (TCC) is an attractive consistency level for building such platforms. TCC avoids many anomalies of eventual consistency, eschews the synchronization costs of strong consistency, and supports interactive read-write transactions. Partial replication is another attractive design choice for building geo-replicated platforms, as it reduces storage requirements and update propagation costs. This paper presents PaRiS, the first TCC system that supports partial replication and implements non-blocking parallel read operations. The latter reduce read latency which is of paramount importance for the performance of read-intensive applications. PaRiS relies on a novel protocol to track dependencies, called Universal Stable Time (UST). By means of a lightweight background gossip process, UST identifies a snapshot of the data that has been installed by every data center (DC) in the system. Hence, transactions can consistently read from such a snapshot on any server in any replication site without having to block. Moreover, PaRiS requires only one timestamp to track dependencies and define transactional snapshots, thereby achieving resource efficiency and scalability. We evaluate PaRiS on an AWS deployment composed of up to 10 replication sites. We demonstrate a performance gain of non-blocking reads vs. a blocking alternative (up to 1.47x higher throughput with 5.91x lower latency for read-dominated workloads and up to 1.46x higher throughput with 20.56x lower latency for write-heavy workloads). We also show that the throughput penalty incurred to implement causal consistency, compared to variant without the causal consistency guarantees, is as low as 20% for read-heavy workloads and 37% for write-heavy workloads. We furthermore show that PaRiS scales well with the number of DCs and partitions, while being able to handle larger data-sets than existing solutions that assume full replication.

IEEE COMPUTER SOC2019

, ,

In a modern data center (DC), a large majority of costs arise from energy consumption. The most popular technique used to mitigate this issue is virtualization and more precisely virtual machine (VM) consolidation. Although consolidation may increase server usage by about 5-10%, it is difficult to actually witness server loads greater than 50%. By analyzing the traces from our cloud provider partner, confirmed by previous research work, we have identified that some VMs have sporadic moments of data computation followed by large periods of idleness. These VMs often hinder the consolidation system which cannot further increase the energy efficiency of the DC. In this paper we propose a novel DC power management system called Drowsy-DC, which is able to identify the aforementioned VMs which have matching patterns of idleness. These VMs can thus be colocated on the same server so that their idle periods are exploited to put the server to a low power mode (suspend to RAM) until some data computation is required. While introducing a negligible overhead, our system is able to significantly improve any VM consolidation system; evaluations showed improvements up to 81% and more when compared to OpenStack Neat.

IEEE2019

Recommender System for Responsive Engagement of Senior Adults in Daily Activities

Igor Kulev, Yuan Lu, Pearl Pu Faltings

Understanding and predicting how people change their behavior after an intervention from time series data is an important task for health recommender systems. This task is especially challenging when the time series data is frequently sampled. In this paper, we develop and propose a novel recommender system that aims to promote physical activeness in elderly people. The main novelty of our recommender system is that it learns how senior adults with different lifestyle change their activeness after a digital health intervention from minute-by-minute fitness data in an automated way. We trained the system and validated the recommendations using data from senior adults. We demonstrated that the low-level information contained in time series data is an important predictor of behavior change. The insights generated by our recommender system could help senior adults to engage more in daily activities.

SPRINGER INTERNATIONAL PUBLISHING AG2020