Preference Bias Research Articles

Pterin-Based Red Coloration Predicts the Outcome of Male-Male Competition in Guinan Toad-Headed Lizard.

Animal coloration offers a unique opportunity to explore the evolutionary mechanisms underlying phenotypic diversity. Conspicuous coloration caused by pigments plays a crucial role in social signaling across multiple species by conveying information about individual quality, social ranks, or reproductive condition. Nevertheless, most previous studies have focused predominantly on colors produced by the exogenous pigments-carotenoids. Pterins are another prevalent group of conspicuous pigments, which can be produced endogenously and have received comparatively little attention. Whether pterin-based colors represent reliable signals remains elusive. The remarkable red ventrolateral coloration exhibited by males of the Guinan toad-headed lizard (Phrynocephalus guinanensis) in the Mugetan Desert presents an ideal model for investigating pterin-based coloration. Through electron microscopy and metabolomic identification, we discovered three types of pterin pigments within xanthophores. Integrating a series of morphological measurements and behavioral experiments, we found that this red coloration was not correlated with body size, bite force, and testosterone level, nor did females show a preference bias toward it. However, the red intensity predicted male-male competition outcomes, with deeper red males being more likely to emerge as winners. Our results indicated that the pterin-based coloration could convey information about male quality, suggesting its potential role in honest signaling, given the vital importance of pterin metabolism in physiological processes. This study provides a novel case into the understanding of pterin-based colors in animals.

The relationship between interpersonal distance preference and estimation accuracy in autism.

People naturally seek an interpersonal distance that feels comfortable, striking a balance between not being too close or too far from others until reaching a state of equilibrium. Previous studies on interpersonal distance preferences among autistic individuals have yielded inconsistent results. Some show a preference for greater distance, while others indicate a preference for shorter distances, or reveal higher variance in preferences among autistic individuals. In a related vein, previous studies have also investigated the way autistics accurately judge distance, and these studies have received inconsistent results, with some showing superior spatial abilities and others indicating biases in distance estimations. However, the link between distance estimation and preference has never been examined. To address this gap, our study measured interpersonal distance preferences and estimations and tested the correlation between the two factors. The results indicate greater variance among autistic people in both the preference of distance and the ability to estimate distance accurately, suggesting that inconsistencies in previous studies originate from greater individual differences among autistics. Furthermore, only among autistic individuals were interpersonal distance preference and estimation bias associated in a manner that violated equilibrium. Underestimation bias (judging others as closer than they are) was linked to a preference for closer proximity, while overestimation bias (judging others as further away) was associated with a preference for maintaining a greater distance. This connection suggests that biases in the estimation of interpersonal distance contribute to extreme preferences (being too close or too far away). Taken together, the findings suggest that biases in the estimation of interpersonal distance are associated with socially inappropriate distance preferences among autistics.

Logistical and preference bias in participatory science butterfly data

The volume of and interest in unstructured participatory science data has increased dramatically in recent years. However, unstructured participatory science data contain taxonomic biases—encounters with some species are more likely to be reported than encounters with others. Taxonomic biases are driven by human preferences for different species and by logistical factors that make observing certain species challenging. We investigated taxonomic bias in reports of butterflies by characterizing differences between a dedicated participatory semi‐structured dataset, eButterfly, and a popular unstructured dataset, iNaturalist, in spatiotemporally explicit models. Across 194 butterfly species, we found that 53 species were overreported and 34 species were underreported in opportunistic data. Ease of identification and feature diversity were significantly associated with overreporting in opportunistic sampling, and strong patterns in overreporting by family were also detected. Quantifying taxonomic biases not only helps us understand how humans engage with nature but also is necessary to generate robust inference from unstructured participatory data.

Unearned Inequality and Biased Distributional Preferences: Evidence from a Lab Experiment in Ghana

I use a dictator game, with a preceding production phase, to explore how different sources of unearned inequality influence distribution decisions. The experiment introduces three inequalities: (1) inequality due to investment success, (2) inequality of initial endowments, and (3) inequality in a real-effort task requirement for receiving the initial endowment. I find that participants in rural Ghana respect each inequality, adjusting their allocation decisions in response to investment success, the distribution of initial endowments, and the effort requirement. Their distributional preferences suggest an interaction between the sources where those with high initial endowments are more likely to respect project success outcomes. Moreover, participants demonstrate a self-serving bias in fairness preferences, where those with high initial endowments and successful projects are more likely to respect inequality. Finally, I find a significant increase in self-allocations when participants must exert effort to receive their endowment.

Disparities and outcomes of immune checkpoint inhibitor therapies in LMICs: Retrospective study on current state, efficacy, and challenges in Armenia.

e23315 Background: The escalating incidence of cancer in Armenia is a global trend, underscoring the urgency for innovative treatments, including immune checkpoint inhibitors (ICIs). This study, a first in the region, investigates ICIs' real-world impact, emphasizing the current state and critical gaps in access to care. Methods: We conducted a retrospective review of 224 patients, excluding 32, resulting in 192 patients treated with ICIs between 2017 and 2023 across four major oncology centres. The review covered demographic and clinical data, genetic testing, treatment regimens, and survival outcomes, analyzed using the STATA 18 BE. Results: The mean age of the patients was 61.4 years, with 69.27% being male. Lung cancer was the most common diagnosis (42.19%, n = 81), followed by melanoma (11.98%, n = 23) and gastric cancer (10.94%, n = 21). Survival outcomes varied, with melanoma patients exhibiting a mean overall survival (OS) of 33.26 months, lung cancer patients 19.69 months, and gastric cancer patients 20.50 months; the survival difference between patients with metastases and without was not statistically significant. Patients receiving ICIs in the second or later lines of treatment had a 2.12-fold lower chance of survival compared to those receiving them as first-line treatment (95% CI 1.16-3.88, p = 0.014). 78% of patients received ICIs in the metastatic setting and only 22% in curative. In two centres, among 185 patients with metastatic lung cancer, only 23.2% (43 patients) received ICIs, and of these, about 50% underwent mutation testing, with only 4 assessed via broad panel NGS. A significant 76.8% (142 patients) did not receive immunotherapy. Furthermore, 34% of those starting ICI treatment were forced to discontinue due to financial hardships. Pembrolizumab and Nivolumab were the most widely used agents, but the choice varies significantly between centres. Conclusions: The financial barrier is substantial: the cost of one pembro cycle on the black market, at $3,000, is 3.8 times the annual income of those at the national poverty line, more than twice the income of the lower middle-income class, and represents over 60% of the country's GDP per capita. Median cycle lengths for ICIs, such as 6.5 for Ipil+Nivo and 5.61 for Pembro, are below the NCCN's standard recommendations, highlighting the profound impact of financial constraints on treatment adherence and duration. This study reveals the stark reality of ICI accessibility and affordability in Armenia, where a significant portion of cancer patients are unable to benefit from these potentially life-extending treatments. Additionally, a preference bias towards selecting treatments without nationwide guidelines was observed, alongside the absence of a national E-health database, underscoring the need for policymaker attention, insurance adjustments, and more precise, prospective data collection.

A powerful local government's optimal discretion in simple menu contract of monopoly regulation

We analyse the optimal discretion of a powerful local government (LG) in deciding the instrument choice and setting standards of simple menu contracts (composed of a fixed price and a cost reimbursement) of monopoly regulation. Between the two, a fixed-price contract entails more incentives for efficiency than a cost-reimbursement contract, but ensures more profits for the firm. Due to a preference bias towards the firm's benefits between governments, an incentive reward, offered by the federal government (FG) to the powerful LG with informational advantage of efficiency gain from the regulation, is considered to induce an efficient regulatory policy. We find that under the FG's delegation mechanism, upper-level government conflict leads to a compromised policy as an exchange payoff and additional informational rent to the LG for part of their information value. For the remaining information, the reward is rejected, and the LG has the discretionary power to set policy criteria for simple contracts. The results suggest that bureaucratic political issues still lead to an excessive tendency towards either a fixed price or cost reimbursement scheme, depending on the bias direction of the LG's preferences regarding the monopoly. However, the delegation mechanism of hierarchical bureaucracy can effectively alleviate the influence of policy distortions caused by political factors.

SON PREFERENCE, FAMILY CONTROL AND FAMILY MEMBER SELECTION BIAS: EVIDENCE FROM CHINESE LISTED FAMILY FIRMS

This study investigates the influence of regional culture on local family firms from the perspective of son preference. By analyzing a sample of all 604 family firms listed on the China Shenzhen Stock Exchange, this study finds that in areas where son preference is pervasive, local family firms will give priority to introducing sons rather than daughters into the firm, and are more likely to hire a family CEO and hold more control of the firm in order to strengthen family control. Meanwhile, family firms in areas where there is a high preference for sons over daughters are also more inclined to choose close rather than distant relatives, and blood rather than affinity relatives into firms. This study contributes to this research by exploring the influence of local culture on family firms and verifying that family members are not a group with consistent interests; some family members are always given higher priority within the family. In addition, most research assumes that family firms in China are homogeneous; we demonstrate heterogeneity across China within different regions.

Simultaneous profiling of chromatin accessibility and DNA methylation in complete plant genomes using long-read sequencing.

Epigenetic regulations, including chromatin accessibility, nucleosome positioningand DNA methylation intricately shape genome function. However, current chromatin profiling techniques relying on short-read sequencing technologies fail to characterise highly repetitive genomic regions and cannot detect multiple chromatin features simultaneously. Here, we performed Simultaneous Accessibility and DNA Methylation Sequencing (SAM-seq) of purified plant nuclei. Thanks to the use of long-read nanopore sequencing, SAM-seq enables high-resolution profiling of m6A-tagged chromatin accessibility together with endogenous cytosine methylation in plants. Analysis of naked genomic DNA revealed significant sequence preference biases of m6A-MTases, controllable through a normalisation step. By applying SAM-seq to Arabidopsis and maize nuclei we obtained fine-grained accessibility and DNA methylation landscapes genome-wide. We uncovered crosstalk between chromatin accessibility and DNA methylation within nucleosomes of genes, TEs, and centromeric repeats. SAM-seq also detects DNA footprints over cis-regulatory regions. Furthermore, using the single-molecule information provided by SAM-seq we identified extensive cellular heterogeneity at chromatin domains with antagonistic chromatin marks, suggesting that bivalency reflects cell-specific regulations. SAM-seq is a powerful approach to simultaneously study multiple epigenetic features over unique and repetitive sequences, opening new opportunities for the investigation of epigenetic mechanisms.

The consistency principle: Crisis perceptions, partisanship and public support for democratic norms in comparative perspective

AbstractA growing body of research theorizes that partisanship can undermine democracy as citizens prioritize their political interests over abstract norms and values. We argue that crises might counteract intense partisanship by giving citizens clarity on the threats posed by rule of law violations. Examining the differential application of a law – a breach of democratic norms – we draw on an experiment embedded in representative surveys of Germany, the United States, Hungary and Poland to examine citizens’ sense of appropriate punishment for elites’ violation of a municipal mask‐wearing ordinance. We find evidence of partisan bias in citizens’ willingness to support punishment in all four countries. But, in the two consolidated democracies, we find that concern about the Covid‐19 crisis diminishes partisan biases in punishment preferences: citizens who are most concerned about the crisis also model the most consistency in their willingness to hold copartisans into account.

The impact of circumscribed interest distractors on attentional orienting in young children with autism: eye-tracking evidence from the remote distractor paradigm

ABSTRACT Studies from free-viewing tasks report that children with autism spectrum condition (ASC) exhibit an attentional bias for circumscribed interest (CI) objects (e.g., vehicles) over non-CI objects (e.g., furniture). This atypical preference has led researchers to hypothesise that ASC children would be more distracted by CI-related objects than non-CI-related objects. The current study aimed to explore this issue using a remote distractor paradigm. We found longer saccade latencies for centrally presented distractors in ASC, suggesting delayed endogenous disengagement. Additionally, higher error rates and fewer corrective saccades in ASC indicated poorer attentional control. Neither latencies nor errors were modulated by stimulus types but increased dwell time for CI-related objects over non-CI-related objects in ASC, demonstrated some support for the CI attentional bias reported in previous free-viewing studies. The findings are discussed in relation to how task demands in basic orienting paradigms might mask any CI-related preference bias in children with ASC.

Dual-channel representation consistent recommender for session-based new item recommendation

Session-Based Recommendations (SBR) have become a crucial branch in the recommendation field. Usually, most previous SBR methods only recommend items existing in users’ historical sessions, facing difficulties with uninteracted items. Introducing new items to users is essential, but solving this issue termed as “Session-based New Item Recommendation (SNIR)” is not an easy task. The complexity arises from accurately characterizing new items and predicting user preferences without user-item interactions. To tackle these challenges, we propose a simple yet effective model named Dual-Channel Representation Consistent Recommender (DC2R). We design a dual-channel strategy to effectively model a new item by its ontology information and inferred representation. Specifically, the ontology information is captured by integrating the inherent attributes of the item into the learning. Meanwhile, leveraging the zero-shot learning technique, we can obtain the inferred item representation from additional attributes. Dual preferences are extracted from the two representations separately to avoid preference bias issues. To better mine user preferences, a Representation Consistent Encoder is utilized to ensure that user preferences and item representations are in the same linear space, thus more precisely reflecting users’ interests. Experiments are conducted on three representative real-world datasets, and the results demonstrate the effectiveness of our proposed method. The source code of our proposed model is available at https://github.com/codeCyw/DC2R.

Investigating global brand preference bias among low-status consumers

Objective - This study reconciles system justification theory (SJT), intersectionality awareness (IA), and dual attitudes (DA) to determine the conscious-unconscious relationship between consumer identity and global brand preference bias in low-status consumers. Method - We performed three experimental studies: First, we observed the discrepancy between explicit/conscious and implicit/unconscious (DA) global brand attitudes according to established social order (SJT), even if a status quo bias exerts influence. Second, we propose the moderation of the disidentification, which emphasizes the rejection of local elements in this process. Lastly, we propose the mitigation of the disidentification effects through status quo awareness, or Intersectionality Awareness (IA). Relevance/originality – The literature of low-status consumers’ identity relation to brand preference is still developing when tapping multiple layers of perspectives, such as disidentification and identity awareness, and conscious and unconscious processes. The comprehension of this interaction allows a better understanding of the global brand preference bias. Main results – We identified conflicting conscious and unconscious global brand attitudes, potentialized through disidentification with domestic values, those that represent the home country consumer, although their effect can be mitigated by intersectionality awareness. Theoretical/methodological contributions – Theoretically, this study advances the knowledge about global brand preference, including the status quo/awareness theory to better understand the customer-brand relationship. Methodologically, we advanced by employing an unconscious-based technique to address the phenomenon. Social/management contributions – The study explains brand preference bias through the mechanism of disidentification, and their control through social awareness, expanding practitioners’ horizons beyond brand strategies, to consider deep human identity mechanisms. For the individuals and the society, the study proposes understanding on the potential side effects of consumer-brand relationships, presenting coping strategies to deal with this phenomenon, promoting more equality and inclusion.

Characterizing the Retailer's Preference for Demand–Control and Demand–Promotion Efforts

This article investigates a setting where the retailer invests costly effort to shape demand, such as reducing demand fluctuation through demand–control effort or increasing demand levels with demand–promotion effort. We explore the preference bias between these two effort types and examine the impact of such a bias on profit performance. The experimental findings reveal that actual effort investments exhibit a significant preference bias for promotion effort in the low-profit condition, while no significant preference bias is observed in the high-profit condition. This behavioral pattern can be captured by a reference-dependent behavioral model incorporating the retailer's optimism level in the reference point. Additional analyses, such as robustness experiments and model extensions, provide further support for the promotion-effort bias in the low-profit condition. Our analysis presents a comprehensive understanding of demand-shaping effort preferences and extends the application of the reference-dependence framework. It provides insights for managers in identifying potential biases and mitigating profit loss in demand-shaping activities.

A novel image database for social concepts reveals preference biases in autistic spectrum in adults and children.

Human beings display the extraordinary ability of grasping and communicating abstract concepts. Yet, no standardized instruments exist to assess this ability. Developing these tools is paramount for understanding abstract representations such as social concepts, with ramifications in educational and clinical settings. Here, we developed an image database depicting abstract social concepts varying in social desirability. We first validated the image database in a sample of neurotypical participants. Then, we applied the database to test different hypotheses regarding how social concepts are represented across samples of adults and children with autism spectrum condition (ASC). Relative to the neurotypicals, we did not observe differences related to ASC in identification performance of the social desirability of the concepts, nor differences in metacognitive ability. However, we observed a preference bias away from prosocial concepts that was linked to individual autistic traits in the neurotypicals, and higher in ASC relative to the neurotypicals both in adults and children. These results indicate that abstract representations such as social concepts are dependent on individual neurodevelopmental traits. The image database thus provides a standardized assessment tool for investigating the representation of abstract social concepts in the fields of psycholinguistics, neuropsychology, neuropsychiatry, and cognitive neuroscience, across different cultures and languages.

Serotonin 4 receptor brain binding and oxytocin-promoted affective and social cognition in healthy women – A randomized controlled trial

BackgroundOxytocin is a neuropeptide known for its prosocial properties and role in social bonding, and intervention with intranasal oxytocin is posited to modulate affective and social cognition (i.e., hot cognition). Serotonin (5-HT) neurotransmission is also involved in emotional and social behaviors and appear to work in concert with oxytocin. However, this interaction so far remains elusive in humans. Therefore, we here investigate the relation between brain 5-HT 4 receptor (5-HT4R) levels and oxytocin-modulated hot cognition. MethodsUsing a double blind, placebo-controlled, randomized crossover design, 35 healthy women received a dose of 24 IU intranasal oxytocin or placebo one month apart. The women were naturally cycling and to control for hormonal fluctuations across the menstrual cycle, intervention days were placed during the early follicular phase. Following intervention cognitive domains including affective memory, affective bias in emotion processing, moral emotions and social information preference were assessed. In a subgroup (n = 25), Positron Emission Tomography (PET) was used to image 5-HT4R brain binding at baseline with the [11C]SB207145 radiotracer. ResultsNo effect of oxytocin intervention relative to placebo was observed for any of the cognitive outcomes. Likewise, regional brain 5-HT4R binding at baseline was not associated with cognitive responses to oxytocin intervention. ConclusionOur data suggest that intervention with intranasal oxytocin does not have an overall effect on hot cognition in healthy women and further that 5-HT4R brain architecture does not mediate cognitive effects of oxytocin in the healthy state.

Distinguishing the role of positivity bias, cognitive impairment and emotional reactivity in the deontological preference in multiple sclerosis during moral dilemmas: a social cognition study protocol.

Multiple sclerosis (MS) is a chronic inflammatory and neurodegenerative disease of the central nervous system characterized by a broad and unpredictable range of symptoms, including cognitive and sociocognitive dysfunction. Among these social-cognitive functions, moral judgment has been explored in persons with MS (PwMS) using moral dilemmas, where participants must decide whether to sacrifice one person to save a greater number. Opting for such a sacrifice reflects utilitarian reasoning (sacrificing one for the benefit of many is deemed acceptable), while refusing reflects deontological reasoning (such sacrifice is considered morally wrong). Compared to controls, PwMS have been shown to make greater deontological moral choices in such dilemmas. While PwMS have demonstrated a higher tendency for deontological moral choices in moral dilemmas compared to controls, the underlying determinants of this reasoning pattern remain unclear. In this project, we aim to investigate cognitive, emotional, and motivational factors that may explain deontological decision-making in MS. We will recruit a sample of 45 PwMS and 45 controls aged 18-55 years. The type of response, deontological or utilitarian, to a series of 20 vignettes of moral dilemmas will constitute the primary outcomes. Global cognitive performance, positivity bias, alexithymia and empathy levels as well as emotional reactivity measured by electrodermal activity (EDA) during moral dilemmas will be secondary outcomes. Ethics approval was granted by a national ethical committee (CPP Ouest III, national number 2023-A00447-38). The project is sponsored by the ARSEP Foundation. Findings will be presented at national and international conferences, as well as published in peer-reviewed scientific journals.

Inferring trip purposes and mode substitution effect of rental e-scooters in London

The lack of information on trip purpose and alternative mode in micromobility service usage data remains a major analytical challenge. Conventional survey method is subject to significant sampling and stated preference biases. To overcome this challenge, this paper presents a new inference method through a case study of rental e-scooters in London. The inference method features a rule-based algorithm for matching observed rental e-scooter trips with filtered trip samples in the English National Travel Survey (NTS) series. Probability distribution of trip purposes and alternative modes are then retrieved from NTS. Inference results are validated using official data. Discrepancies, sources of biases and correction measures are investigated. Based on the inferred mode substitution pattern, we estimate greenhouse gas emissions reduction of selected rental e-scooter trips in London (36–103 g CO2e per mile). It is expected that the proposed method is applicable to a wide range of micromobility studies using service usage data.

Improved Diversity-Promoting Collaborative Metric Learning for Recommendation.

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to introduce a set of multiple representations for each user in the system where users' preference toward an item is aggregated by taking the minimum item-user distance among their embedding set. Specifically, we instantiate two effective assignment strategies to explore a proper quantity of vectors for each user. Meanwhile, a Diversity Control Regularization Scheme (DCRS) is developed to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could induce a smaller generalization error than traditional CML. Furthermore, we notice that CML-based approaches usually require negative sampling to reduce the heavy computational burden caused by the pairwise objective therein. In this paper, we reveal the fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective and then develop an effective sampling alternative for the CML-based paradigm. Finally, comprehensive experiments over a range of benchmark datasets speak to the efficacy of DPCML.

Plant adaptive strategy influences hydrologic services provisioning by stormwater bioretention

Saturated hydraulic conductivity (Ksat) is a key performance variable in nature-based solutions for managing stormwater such as bioretention. Ksat is well understood from a soils perspective, but not an ecological one, despite growing recognition that plant traits and soil characteristics influence one-another and may co-regulate Ksat. There are myriad plant traits that potentially influence Ksat, which makes it difficult to know where attention should be focused to inform hydrologic design. We address this knowledge gap by 1) evaluating adaptive strategy theory as an overarching framework for characterizing plant effects on Ksat, assessing fifteen bioretention systems across three U.S. states and 2), exploring the implications of this theory for spatial and temporal patterns in plant effects on Ksat driven by regional variability in planting guidance and trajectories of plant succession. Our results illustrate that adaptive strategy significantly influences Ksat, with ruderal plants tending to decrease it and stress tolerant or competitive/stress tolerant plants increasing it. These relationships are indirect, reflecting the impact of adaptive strategy on root traits and soil organic matter, which influence Ksat directly. When these relationships are evaluated in the context of established planting guidance, we find that plants recommended in arid climates tend to increase Ksat relative to bare filter media whereas plants in humid climates do not. Small biases in planting preferences can dramatically change these outcomes. For instance, established vegetation in our bioretention sites was more competitive/stress tolerant than expected, significantly increasing Ksat. We also find that plant effects on Ksat are likely to vary in response to ruderal recruitment as bioretention systems age, reducing Ksat up to 15 %. Collectively, these results illustrate that plants play an important role in bioretention hydrology, and warrant consideration during hydrologic design. They also suggest that adaptive strategy theory is a promising design tool, providing useful insights into plant effects on Ksat, both geographically and over time.

Longitudinal Impact of Preference Biases on Recommender Systems’ Performance

Recommender systems are ubiquitous on various online platforms and provide significant value to the users in helping them find relevant content/items to consume. After item consumption, users can often provide feedback (i.e., their preference ratings for the item) to the system. Research studies have shown that recommender systems’ predictions, observed by users, can cause biases in users’ postconsumption preference ratings. Because these ratings are typically fed back to the system as training data for future predictions, this process is likely to influence the system’s performance over time. We use a simulation approach to investigate the longitudinal impact of preference biases on the dynamics of recommender systems’ performance. Our results reveal that preference biases significantly impair recommendation performance and users’ consumption outcomes, and larger biases cause disproportionately large negative effects. Additionally, less popular and less distinctive (in terms of their content) items are more susceptible to preference biases. Furthermore, considering the substantial impact of preference biases on recommendation performance, we examine the issue of debiasing user-submitted ratings. We find that relying solely on historical rating data is unlikely to be effective in debiasing; thus, we propose/evaluate new debiasing approaches that use additional relevant information that can be collected by recommendation platforms.