Longstanding data labeling practices in machine learning involve collecting and aggregating labels from multiple annotators. But what should we do when annotators disagree? Though annotator disagreement has long been seen as a problem to minimize, new perspectivist approaches challenge this assumption by treating disagreement as a valuable source of information. In this position paper, we examine practices and assumptions surrounding the causes of disagreement--some challenged by perspectivist approaches, and some that remain to be addressed--as well as practical and normative challenges for work operating under these assumptions. We conclude with recommendations for the data labeling pipeline and avenues for future research engaging with subjectivity and disagreement.
Recommender systems play a pivotal role in helping users navigate an overwhelming selection of products and services. On online platforms, users have the opportunity to share feedback in various modes, including numerical ratings, textual reviews, and likes/dislikes. Traditional recommendation systems rely on users explicit ratings or implicit interactions (e.g. likes, clicks, shares, saves) to learn user preferences and item characteristics. Beyond these numerical ratings, textual reviews provide insights into users fine-grained preferences and item features. Analyzing these reviews is crucial for enhancing the performance and interpretability of personalized recommendation results. In recent years, review-based recommender systems have emerged as a significant sub-field in this domain. In this paper, we provide a comprehensive overview of the developments in review-based recommender systems over recent years, highlighting the importance of reviews in recommender systems, as well as the challenges associated with extracting features from reviews and integrating them into ratings. Specifically, we present a categorization of these systems and summarize the state-of-the-art methods, analyzing their unique features, effectiveness, and limitations. Finally, we propose potential directions for future research, including the integration of multi-modal data, multi-criteria rating information, and ethical considerations.
The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. With unbiasedness comes potentially high variance, and prevalent methods exist to reduce estimation variance. These methods typically make use of control variates, either additive (i.e., baseline corrections or doubly robust methods) or multiplicative (i.e., self-normalisation). Our work unifies these approaches by proposing a single framework built on their equivalence in learning scenarios. The foundation of our framework is the derivation of an equivalent baseline correction for all of the existing control variates. Consequently, our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it. This optimal estimator brings significantly improved performance in both evaluation and learning, and minimizes data requirements. Empirical observations corroborate our theoretical findings.
Most modern recommendation algorithms are data-driven: they generate personalized recommendations by observing users' past behaviors. A common assumption in recommendation is that how a user interacts with a piece of content (e.g., whether they choose to "like" it) is a reflection of the content, but not of the algorithm that generated it. Although this assumption is convenient, it fails to capture user strategization: that users may attempt to shape their future recommendations by adapting their behavior to the recommendation algorithm. In this work, we test for user strategization by conducting a lab experiment and survey. To capture strategization, we adopt a model in which strategic users select their engagement behavior based not only on the content, but also on how their behavior affects downstream recommendations. Using a custom music player that we built, we study how users respond to different information about their recommendation algorithm as well as to different incentives about how their actions affect downstream outcomes. We find strong evidence of strategization across outcome metrics, including participants' dwell time and use of "likes." For example, participants who are told that the algorithm mainly pays attention to "likes" and "dislikes" use those functions 1.9x more than participants told that the algorithm mainly pays attention to dwell time. A close analysis of participant behavior (e.g., in response to our incentive conditions) rules out experimenter demand as the main driver of these trends. Further, in our post-experiment survey, nearly half of participants self-report strategizing "in the wild," with some stating that they ignore content they actually like to avoid over-recommendation of that content in the future. Together, our findings suggest that user strategization is common and that platforms cannot ignore the effect of their algorithms on user behavior.
The Probability Ranking Principle (PRP) has been considered as the foundational standard in the design of information retrieval (IR) systems. The principle requires an IR module's returned list of results to be ranked with respect to the underlying user interests, so as to maximize the results' utility. Nevertheless, we point out that it is inappropriate to indiscriminately apply PRP through every stage of a contemporary IR system. Such systems contain multiple stages (e.g., retrieval, pre-ranking, ranking, and re-ranking stages, as examined in this paper). The \emph{selection bias} inherent in the model of each stage significantly influences the results that are ultimately presented to users. To address this issue, we propose an improved ranking principle for multi-stage systems, namely the Generalized Probability Ranking Principle (GPRP), to emphasize both the selection bias in each stage of the system pipeline as well as the underlying interest of users. We realize GPRP via a unified algorithmic framework named Full Stage Learning to Rank. Our core idea is to first estimate the selection bias in the subsequent stages and then learn a ranking model that best complies with the downstream modules' selection bias so as to deliver its top ranked results to the final ranked list in the system's output. We performed extensive experiment evaluations of our developed Full Stage Learning to Rank solution, using both simulations and online A/B tests in one of the leading short-video recommendation platforms. The algorithm is proved to be effective in both retrieval and ranking stages. Since deployed, the algorithm has brought consistent and significant performance gain to the platform.
With recent studies related to Neural Networks being used on different forecasting and time series investigations, this study aims to expand these contexts to ferry passenger traffic. The primary objective of the study is to investigate and evaluate an LSTM-based Neural Networks' capability to forecast ferry passengers of two ports in the Philippines. The proposed model's fitting and evaluation of the passenger flow forecasting of the two ports is based on monthly passenger traffic from 2016 to 2022 data that was acquired from the Philippine Ports Authority (PPA). This work uses Mean Absolute Percentage Error (MAPE) as its primary metric to evaluate the model's forecasting capability. The proposed LSTM-based Neural Networks model achieved 72% forecasting accuracy to the Batangas port ferry passenger data and 74% forecasting accuracy to the Mindoro port ferry passenger data. Using Keras and Scikit-learn Python libraries, this work concludes a reasonable forecasting performance of the presented LSTM model. Aside from these notable findings, this study also recommends further investigation and studies on employing other statistical, machine learning, and deep learning methods on forecasting ferry passenger flows.
Given the increasing demand for mental health assistance, artificial intelligence (AI), particularly large language models (LLMs), may be valuable for integration into automated clinical support systems. In this work, we leverage a decision transformer architecture for topic recommendation in counseling conversations between patients and mental health professionals. The architecture is utilized for offline reinforcement learning, and we extract states (dialogue turn embeddings), actions (conversation topics), and rewards (scores measuring the alignment between patient and therapist) from previous turns within a conversation to train a decision transformer model. We demonstrate an improvement over baseline reinforcement learning methods, and propose a novel system of utilizing our model's output as synthetic labels for fine-tuning a large language model for the same task. Although our implementation based on LLaMA-2 7B has mixed results, future work can undoubtedly build on the design.
Objective: We report the development of the patient-centered myAURA application and suite of methods designed to aid epilepsy patients, caregivers, and researchers in making decisions about care and self-management. Materials and Methods: myAURA rests on the federation of an unprecedented collection of heterogeneous data resources relevant to epilepsy, such as biomedical databases, social media, and electronic health records. A generalizable, open-source methodology was developed to compute a multi-layer knowledge graph linking all this heterogeneous data via the terms of a human-centered biomedical dictionary. Results: The power of the approach is first exemplified in the study of the drug-drug interaction phenomenon. Furthermore, we employ a novel network sparsification methodology using the metric backbone of weighted graphs, which reveals the most important edges for inference, recommendation, and visualization, such as pharmacology factors patients discuss on social media. The network sparsification approach also allows us to extract focused digital cohorts from social media whose discourse is more relevant to epilepsy or other biomedical problems. Finally, we present our patient-centered design and pilot-testing of myAURA, including its user interface, based on focus groups and other stakeholder input. Discussion: The ability to search and explore myAURA's heterogeneous data sources via a sparsified multi-layer knowledge graph, as well as the combination of those layers in a single map, are useful features for integrating relevant information for epilepsy. Conclusion: Our stakeholder-driven, scalable approach to integrate traditional and non-traditional data sources, enables biomedical discovery and data-powered patient self-management in epilepsy, and is generalizable to other chronic conditions.
With the recent success of large language models, particularly foundation models with generalization abilities, applying foundation models for recommendations becomes a new paradigm to improve existing recommendation systems. It becomes a new open challenge to enable the foundation model to capture user preference changes in a timely manner with reasonable communication and computation costs while preserving privacy. This paper proposes a novel federated adaptation mechanism to enhance the foundation model-based recommendation system in a privacy-preserving manner. Specifically, each client will learn a lightweight personalized adapter using its private data. The adapter then collaborates with pre-trained foundation models to provide recommendation service efficiently with fine-grained manners. Importantly, users' private behavioral data remains secure as it is not shared with the server. This data localization-based privacy preservation is embodied via the federated learning framework. The model can ensure that shared knowledge is incorporated into all adapters while simultaneously preserving each user's personal preferences. Experimental results on four benchmark datasets demonstrate our method's superior performance. Implementation code is available to ease reproducibility.
In recommender systems, the presentation of explanations plays a crucial role in supporting users' decision-making processes. Although numerous existing studies have focused on the effects (transparency or persuasiveness) of explanation content, explanation expression is largely overlooked. Tone, such as formal and humorous, is directly linked to expressiveness and is an important element in human communication. However, studies on the impact of tone on explanations within the context of recommender systems are insufficient. Therefore, this study investigates the effect of explanation tones through an online user study from three aspects: perceived effects, domain differences, and user attributes. We create a dataset using a large language model to generate fictional items and explanations with various tones in the domain of movies, hotels, and home products. Collected data analysis reveals different perceived effects of tones depending on the domains. Moreover, user attributes such as age and personality traits are found to influence the impact of tone. This research underscores the critical role of tones in explanations within recommender systems, suggesting that attention to tone can enhance user experience.