Temporal Attributes Research Articles

CONCEPT “SNOW” IN THE LINGUISTIC AND FOLKLORE PICTURE OF THE WORLD OF THE INDIGENOUS PEOPLES OF YAKUTIA

The article undertakes a comparative analysis of the concept “Snow” in the linguistic and folklore worldview of the indigenous peoples of Yakutia. The purpose of the study is to identify the specific features of representation of this concept in the linguistic and folklore worldview of the Yakuts, Evens, Evenki, Yukaghirs. The methods used in the paper include linguocultural analysis, continuous sampling, comparison and collation. Following the research of verbalisation of the concept “Snow”, it was revealed that it is universal and significant in the conceptual framework “Natural phenomena”. It was found that the concept “Snow” in the Yakut linguistic and folkloric world image represents a complex, multilayer formation going beyond the framework of natural phenomena, being capable of expressing figurative meanings involving negative connotations, when designating failure, loss of orientation, deception, tears, as well as measure, quantity, time; act as part of an anthroponym, etc. It was established that the most relevant features are the makeup, depth of snow, time of snowfall, etc., which is important in horse husbandry, cattle breeding and hunting. It was revealed that the concept “Snow” in the Even, Evenki and Yukaghir linguistic world image is presented mainly as a component of the concept “Natural phenomena”, characterising snow in terms of various qualitative, temporal and spatial attributes associated with reindeer breeding and hunting. The explored folklore materials reflecting the life of the Evens, Evenki, Yukaghirs showed that this concept serves mainly as a marker of winter onset, colour white, a component of everyday life activities, of time, sometimes of danger, transience. The work results can be used in the development of theoretical provisions of cultural linguistics, in comparative research of ethno-cultural features of the linguistic and folklore picture of the world of the indigenous peoples of Yakutia.

Application of 5G Internet of Things Multisensor Information Fusion Model in Piano Performance

In this paper, we use melodic multisensor information fusion combined with 5G IoT to conduct an in-depth study and analysis of the experience model of piano performance. In the form of multimodal data, two main storage forms, audio and MIDI, are chosen. First, audio signal processing technology and deep learning technology are used to extract shallow and high-level feature sequences in turn, and then, the alignment of the two modal data is completed with the help of sequence alignment algorithm. For the problem that encrypted data cannot be queried by uploading blockchain, this paper proposes an IoT encrypted data query mechanism based on blockchain and Bloom’s filter. The blockchain stores IoT encrypted indexes by temporal attributes to ensure data consistency, tamper-evident, and traceability. A new loss function training multimodal model is designed for piano performance signals. The piano performance generated by this model differs from the traditional piano performance generation in that it does not need to add complex piano performance rules manually but generates piano performance directly with piano performance theory rules by training the initial piano performance dataset and improves the stability of the generated piano performance by chord constraints and enhances the note dependence on time. In the analysis of the experimental results, the generated melodies were invited 50 for evaluation and analysis. The overall style-based GAN network piano performance generation model proposed in the study makes the generated piano performance melodies more pleasing to the ear through chord constraints and the content of autonomous learning moments, which has important theoretical and practical implications for the creation and realization of mass and batch piano performances.

Harnessing the temporal and projective attributes of human agency to promote anticipatory climate change adaptation

Human agency is seen as a critical component of adaptive capacity concerning environmental change. This capacity may entail social actor's ability to learn from past experience, and create opportunities in the present for dealing with uncertainty and change in the future. However, it also means that actors need to be able to overturn structural barriers that impede anticipatory adaptation to climate change such as lack of political leadership, power imbalances, acceptance of climate risks and willingness to act. While scholarship around questions of structural barriers is common in environmental studies literature, there is less understanding about how future thinking could help to strengthen human agency. Harnessing the temporal and projective attributes of human agency by which social actors can exert influence over the future and create solutions may comprise a promising way forward. This paper investigates how social actors understand past social and environmental change and explores how scenario planning may help actors apply their understanding of changes over time to devise policies for climate change adaptation. The paper applies this exploratory lens to an Australian coastal local government area engaged in scenario planning and adaptation pathways planning. Findings indicate that the temporality aspect of agency applied to solving complex issues and overcoming structural barriers manifests differently from an individual to a collective perspective. This means that while scenario planning and adaptation pathways planning helps with anticipatory identification and experimentation, this may not be sufficient to overturn structural barriers to adaptation in the short-term.

Typology and Modeling Profiles of AS-Class Process-Entity Interactions: Object Actualization and Base Schema Adaptation

The ability of objects engages in specific interactions, as one of the object properties, referred to as readiness (applicability), always restricts by the "windows of capabilities" — the temporal corridors during which these interactions can take place. The beginning and duration of a single corridor, correlated with an object and the predicted interaction, at any given time depends on a finite number of temporal corridors belonging to other objects and interactions. Thus, the coherence of the process-entity interactions ensemble is achieved not only by setting materialization relationships, but also by synchronizing them in time. To study and model readiness, covering all types and associations involved in the interactions of the assembling class, the work uses "On" and "Off" timestamps tied to an abstract timeline. The contributions of our study are threefold. First of all, substantiation in the expediency of using such an object property as readiness in conceptual modeling. Second, the system of generic temporal constraints that secure the data reliability and correctness. Third, the concept of temporal corridors and the method of the latter calculation, which allows you to find acceptable boundaries for changing the values of temporal attributes in case of updating them. We have shown one of the options for adapting the generalized assembly process in a given application domain and the specific domain constraint that can arise in this case using an example from practice.

APPLICATION AND PLATFORM DESIGN OF SPATIOTEMPORAL DATA OPENING AND SHARING

Abstract. Spatiotemporal data is data that has both temporal attributes and spatial distribution. The core of the opening and sharing of spatiotemporal data is to exchange, share and collaborate with various data, including spatiotemporal data, based on a unified spatiotemporal benchmark. The research methods of domestic and foreign scholars on the opening and sharing of spatiotemporal data mainly focus on spatiotemporal data model, database research, big data mining analysis and visual expression. This paper introduces the connotation and current situation of open sharing of spatiotemporal data. The typical applications of spatiotemporal data open sharing are listed and summarized. This paper proposes to build an open sharing platform for spatiotemporal data, and gives the basic requirements of four parts: spatiotemporal benchmark, spatiotemporal modeling big data, cloud computing-based spatiotemporal big data system and supporting environment. Taking the National Platform for Common Geospatial Information Services (TIANDITU) as an example, the main indicators of the spatiotemporal data open sharing platform are given. Finally, the article concludes and points out the opportunities and challenges faced by the open sharing of spatiotemporal data. In order to play a greater role in social public application services and administrative decision-making.

Predictive Analytics Using Machine Learning to Identify ART Clients at Health System Level at Greatest Risk of Treatment Interruption in Mozambique and Nigeria.

A core objective of HIV/AIDS programming is keeping clients on treatment to improve their health outcomes and to limit spread. Machine learning and artificial intelligence can combine client, temporal, and locational attributes to identify which clients are at greatest risk of loss to follow-up (LTFU) and enable health providers to direct support interventions accordingly. The analysis was part of a project funded by U.S. President's Emergency Plan for AIDS Relief and United States Agency for International Development, Data for Implementation, and applied to data from publicly available sources (health facility data, geospatial data, and satellite imagery) and de-identified electronic medical record data on antiretroviral therapy clients in Nigeria and Mozambique. The project applied binary classification techniques using temporal cross-validation to predict the risk that patients would be LTFU. Classifiers included logistic regression, neural networks, and tree-based models. Models showed strong predictive power in both settings. In Mozambique, the best-performing model, a Random Forest, achieved an area under the precision-recall curve of 0.65 compared against an underlying LTFU rate of 23%. In Nigeria, the best-performing model, a boosted tree, achieved an area under the precision-recall curve of 0.52 compared against an underlying LTFU rate of 27%. Machine-learned models outperformed current classification techniques and showed potential to better direct health worker resources toward patients at greatest risk of LTFU. Moreover, models performed equally across sex and age groups, supporting the model's generalizability and wider application.

Assessment of the Potential of Coordinating Two Interacting Monitoring Networks within the Lerma-Santiago Hydrologic System in Mexico

Water quality monitoring networks in the global south often display inefficiencies because monitoring strategies are frequently designed based on subjective professional judgments to define the temporal and spatial attributes of the networks, leading to poor cost–benefit relationships. The Lerma-Santiago Hydrological System (LSHS) in Mexico currently experiences severe environmental degradation caused by uncontrolled pollutant emissions from urban centers, agricultural, livestock, and industrial activities settled in the basin. While both the national and state authorities monitor this hydrological system, there has never been an effort to assess the monitoring efficiency of these two networks. The aim of the present study was to assess through multivariate statistical analyses the potential for coordination between these two interacting networks. For this purpose, two independent large water quality datasets with temporal and spatial attributes measured by two different authorities (the federal and the state) were used to identify those sites where coordination should be rationalized and those parameters that should continue to be monitored. The case study herein presented highlights the duplication in efforts to monitor surface water quality in the Lerma-Santiago hydrologic system, which implies a lack of coordination between the authorities and shows that water quality monitoring networks have not been reassessed since they were first implemented. Furthermore, using the case study of the Lerma-Santiago in Mexico, we expanded on various deficiencies, such as the use of different sampling frequencies and analytical methods by the authorities and inefficient communication among federal and state authorities. This study has revealed a large potential for coordinating two water quality monitoring networks (WQMN) in the Lerma-Santiago Hydrological System and a methodological approach that may be used to assess this potential. Coordination strategies for WQMNs can lead to significant cost reductions, extended network reach, and higher overall data quality in developing countries with limited financial resources and technical capabilities.

Data-Driven Modeling of Randomized Controlled Trial Outcomes.

Anecdotally, 38.5% of clinical outcome descriptions in randomized controlled trial publications contain complex text. Existing terminologies are insufficient to standardize outcomes and their measures, temporal attributes, quantitative metrics, and other attributes. In this study, we analyzed the semantic patterns in the outcome text in a sample of COVID-19 trials and presented a data-driven method for modeling outcomes. We conclude that a data-driven knowledge representation can benefit natural language processing of outcome text from published clinical studies.

Modeling Water Quantity and Quality Nonlinearities for Watershed Adaptability to Hydroclimate Extremes in Agricultural Landscapes

Changing water supplies and demands, inherent to climate fluctuations and human activities, are pushing for a paradigm shift in water management worldwide. The occurrence of extreme hydrometeorological and climate events such as extended wet periods and droughts, compounded with contaminants, impair the access to water resources, demanding novel designs, construction, and management across multiple hydrologic scales and biogeochemical processes. A constraint to studying hydrologic and biogeochemical disturbances and improving best management practices for water quantity and quality at the watershed scale resides in the suitable monitoring, data availability, and the creation of frameworks. We hypothesize that streamflow and contaminants, simulated by the hydrologic model Soil and Water Assessment Tool (SWAT) and evaluated during drought and extended wet periods, capture the nonlinearities of contaminants of multiple biogeochemical complexities, indicating the adaptive abilities of watersheds. Our objectives are to (1) use rain gauge and radar data and linear regression to consolidate long-term precipitation data to simulate streamflow and water quality using the SWAT model in the Shell Creek (SC) watershed, Nebraska, U.S.; (2) use drought and extended wet events analytics on observed and simulated hydroclimate and water quality variables to identify SWAT’s performance; and (3) identify the temporal attributions of streamflow and water quality to complex biogeochemical patterns of variability. We implement a watershed modeling approach using the SWAT model forced with rain gauge and radar to simulate the intraseasonal and interannual variability streamflow, sediments, nutrients, and atrazine loads in the SC watershed. SWAT performance uses a calibration period between 2000 and 2005 and a validation period between 2005 and 2007. We examine the model’s ability to simulate hydrologic and biogeochemical variables in response to dry and extended wet flow regimes. The hydrologic model forced by either radar or rain gages performs similarly in the calibration (NSE = 0.6) and validation (NSE = 0.92) periods. It reproduces medium flows closer to the observations, although it overestimates low–flows up to 0.1 m3/s while underestimates high flows by 1 m3/s. The water quality model shows higher NSE for streamflow and sediments followed by nutrients, whereas it poorly reproduces atrazine. We conclude that seasonal changes and hydroclimate conditions led to the emergence of patterns of variability associated to the nonlinearities and coupling between processes of natural and human-origin sources. As climate change propels the occurrence of hydroclimate extremes, the simulation of water quantity and quality nonlinearities—as properties of complex adaptive hydrologic systems—can contribute to improve the predictability of climate-resilient water resources.

Trends, intensification, attribution and uncertainty of projected heatwaves in India

AbstractThis study investigates the projected heatwaves for India using 0.25° × 0.25° summer mean temperature data from Coupled Model Intercomparison Project (CMIP) 5 and 6 simulations for 2016–2100. The heatwaves were delineated using count and density‐based indices. A new approach of using medians of past as threshold for computing projected variables was introduced to amplify the footprint of the warming signal on the heatwaves. Further, spatio‐climatic heterogeneity of India was accounted through optimizing climatic zones using the fuzzy c‐mean clustering technique. Temporal homogeneity, trend, intensification and attribution of the heatwave variables were computed and analysed. Additionally, the scenario uncertainty was partitioned from the internal climatic variability, and consequently the variables were modelled within a probabilistic framework. Within this probabilistic framework, a novel concept of intensification ratio was introduced to capture the cost of climate action/inaction on heatwaves in India. All the heatwave variables except heatwave count have breaks in homogeneity between 2045 and 2055 and show predominantly increasing trends. While heatwave count shows an intensification of 4–6 times over the past, with 70% of the intensification being attributable to climate change, for other variables, the figures are 35–30 times and 95%. The scenario uncertainty surpasses the internal climatic variability around 2050. The probabilistic framework yields normalized values of uncertainty mostly below 0.5, enhancing the applicability of the results. Finally, the intensification ratio shows that climate inaction will intensify the heatwaves for ~75% of India by ~50–100%. The intensification of heatwave density over its count and relative accentuation of heatwaves resulting from climate inaction are the major takeaways from this study.

Understanding the wider social and economic context of post-earthquake cordons: A comparative case study between Christchurch, Aotearoa (New Zealand) and L’Aquila, Italy

Post-earthquake cordons have been used after seismic events around the world. However, there is limited understanding of cordons and how contextual information such as geography, sociocultural characteristics, economy, and institutional and governance structures affects decisions and operational procedures, including aspects related to spatial and temporal attributes of cordon establishment. This research aims to fill the gap in cordon knowledge through a qualitative comparative case study of two cities: Christchurch, New Zealand (Mw 6.2 earthquake, February 2011) and L’Aquila, Italy (Mw 6.3 earthquake, 2009). Both cities suffered comprehensive damage to their city centers and had cordons established for extended periods of time. Data collection was done through purposive and snowball sampling whereby 23 key informants were interviewed in total. Research participants held expert knowledge in their roles and responsibilities, that is, council members, emergency managers, politicians, business/insurance representatives, academics, and police. Results illustrate that cordons were primarily established to ensure safety of people and to maintain security. The extent and duration of the cordons were affected by the recovery approaches taken in respective cities, that is, in Christchurch demolition was widely undertaken which supported recovery and allowed for faster removal of cordons. In contrast, authorities in L’Aquila placed high value on heritage buildings which led to recovery strategy based on preserving and restoring most of the buildings which extended the duration of cordon. Extended cordons have many similarities but evolve overtime. This evolution of cordons is affected by site-specific needs; thus, cordons should be understood and planned based on contextual realities.

Spatiotemporal Analysis for Age of Information in Random Access Networks Under Last-Come First-Serve With Replacement Protocol

We investigate the age-of-information (AoI) in the context of random access networks, in which transmitters need to send a sequence of information packets to the intended receivers over a shared spectrum. Due to interference, the dynamics at the link pairs will interact with each other over both space and time, and the effects of these spatiotemporal interactions on the AoI are not well understood. In this paper, we straddle queueing theory and stochastic geometry to establish an analytical framework, that accounts for the interplay between the temporal traffic attributes and spatial network topology, for such a study. Specifically, we derive accurate and tractable expressions to quantify the network average AoI as well as the outage probability of peak AoI. Besides, we develop a decentralized channel access policy that exploits the local observation at each node to make transmission decisions that minimize the AoI. Our analysis reveals that when the packet transmissions are scheduled in a last-come first-serve (LCFS) order, whereas the newly incoming packets can replace the undelivered ones, depending on the deployment density, there may or may not exist a tradeoff on the packet arrival rate that minimizes the network average AoI. Moreover, the slotted ALOHA protocol is shown to be instrumental in reducing the AoI when the packet arrival rates are high, yet it cannot contribute to decreasing the AoI in the regime of infrequent packet arrivals. The numerical results also confirm the efficacy of the proposed scheme, where the gain is particularly pronounced when the network grows in size because our method is able to adapt the channel access probabilities with the change of ambient environment.

Accounting for Uncertainty in Regional Flow–Ecology Relationships

Flow–ecology relationships are critical for developing and adaptively managing environmental flows. However, uncertainty often arises from data limitations and an incomplete understanding of the spatial and temporal attributes inherent to each relationship. Accounting for sources of uncertainty is critical given the mounting interest in implementing environmental flows at large scales, often with limited information. We used the South Fork Eel River watershed in northern California as a case study to demonstrate how data gaps and uncertainty in flow–ecology relationships may be better quantified. A rigorous literature review revealed that few flow–ecology relationships related directly to the flow regime, and none spanned the full range of hydrologic or geomorphic variability exhibited across the watershed. Identified data gaps informed several sensitivity analyses within a Bayesian network model which showed that the modeled ecological outcome differed by as much as 50% depending on the type and magnitude of uncertainty. This study presents a general regional framework for quantifying spatial and temporal data gaps that can be applied to other watersheds and information types to improve representation of uncertainty in flow–ecology relationships and to inform environmental flow design.

Personalized Touch-Based Exergame System for Unilateral and Bilateral Rehabilitation Training.

Background: Natural and intuitive interfaces that monitor and promote upper limb task-specific training need to be developed. This article presents the development and testing of a touch-based game system for training and assessment of unilateral (ULR) and bilateral (BLR) reaching movements. Interaction becomes intuitive and simple by introducing in-game touch and pressure onto virtual targets projected on a custom-made large touch panel. Materials and Methods: A custom-made App integrates exergames and a biomechanical model with advanced algorithms for movement analysis. It processes and manages data from a motion-tracking sensor and a large touch panel equipped with 1222 (26 × 47) piezoresistive sensors, including high-speed readout electronics and algorithms to measure touch points and contact forces during fingertip interaction. An experiment was conducted to evaluate the experience, motivation, and movements of healthy and stroke subjects when interacting with the proposed system. The panel height, dispersion of virtual targets, and required contact force were customized based on motor skills of each group of subjects. Results: Both groups of subjects showed high level of motivation and user experience when interacting with the virtual environments. Stroke subjects performed the task slower and traveled a similar path length than healthy subjects, but with shorter range of motion. The mechanical work and potential energy profiles of both groups are consistent with those achieved when reaching real objects. Conclusions: The proposed contact-based exergames are a feasible solution for performing natural and intuitive therapeutic ULR and BLR exercises. They elicit appropriate reaching movements and contact forces in healthy and stroke subjects. The spatial and temporal attributes of the proposed solution can be customized to influence the movement and energy expenditure of specific joints.

Analysis of pedestrian accident injury-severities at road junctions and crossings using an advanced random parameter modelling framework: The case of Scotland

This paper investigates the determinants of injury severities in pedestrian-motor vehicle accidents at signalised and unsignalised junctions, and at physically-controlled and human-controlled crossings in Scotland. The accident data were drawn from the official police crash report database of the UK spanning a period between 2010 and 2018. Correlated random parameter ordered probit models with heterogeneity in the means were developed in order to account for the multi-layered impact of unobserved heterogeneity on statistical estimation. The model estimation results showed that the severities of accident injuries are affected by roadway, location, weather, vehicle, and driver characteristics as well as temporal attributes (including time and day of the accident). Factors such as the urban context, lighting and weather conditions and road surface conditions were found to result in correlated random parameters, thus capturing the intricate, yet interactive effects of unobserved heterogeneity, and particularly the unobserved behavioural response of road users to different traffic control types at junctions and crossings. Vehicle type, driver’s gender and day-of-the-week were observed to influence the random parameters' distributions. Empirically, the results showcase variations in the determinants of injury severities at signalised and unsignalised junctions, and at physically-controlled and human-controlled crossings. Even though most of these variations were related to the magnitude of impact of the determinants, differences in the directional effects on injury severities were also identified, mainly for factors related to weather conditions, hazard presence on the road, and temporal characteristics of the accidents.

Forecasting TV ratings of Turkish television series using a two-level machinelearning framework

TV rating is a numeric estimate of the popularity of television programs. Forecasting TV ratings is considered an important asset for investment planning of media due to its potential of reducing the risks of future ventures. The aim of this study is to develop a machine learning model capable of efficiently forecasting the TV ratings of Turkish TV series in a practical manner. To this end, two prediction models were proposed for forecasting the TV ratings of television series, facilitating an extensive set of features. A contribution of this study is the inclusion of social media-based features using search trends around television series and exploration of the viability of using these features in place of temporal features. The study presents an extensive evaluation of the forecast performance of the proposed models. The performance of the proposed models were evaluated using a data collection composed of ratings and various attributes of series and their episodes aired at prime-time Turkish broadcast during 2014 and 2018. In the experiments, a theoretical forecast performance was first established with the inclusion of temporal features. Next, a set of practical models were proposed, replacing temporal attributes with social media-based attributes, relating to internet popularity and visibility of the series. The experiments show that, the proposed models achieve up to 1.65% error rate for the theoretical setting and 7.06% error rate for the practical setting.

Построение и оформление статьи в «Русско-английском словаре фразеологизмов-эвфемизмов»

The paper aims to identify reliable and generally recognised ways of structuring and formatting an entry in bilingual phraseological dictionaries and monolingual dictionaries of euphemisms, on the basis of which entries are organised in the “Russian-English Dictionary of Euphemistic Phraseological Units”. The work is the first to describe the principles of structuring a dictionary entry in a bilingual dictionary of euphemistic phraseological units, which constitutes scientific novelty of the study. As a result of the study, it has been found that the necessary components of an entry are the accounting for and presentation of all types of variants of Russian euphemistic phraseological units, their paradigmatic relations, functional-stylistic, temporal and territorial attributes.

Is It Possible to Assess Heatwave Impact on Grapevines at the Regional Level with Time Series of Satellite Images?

Unexpected climatic conditions or extreme climatic events in vineyards are a worldwide problem that requires accurate spatial and temporal monitoring. Satellite-based remote sensing is an important source of data to assess this challenge in a climate-change context. This paper provides a first insight into the capacity of a multiway analysis method applied to Sentinel-2 time series to assess heatwave impacts in vineyards at a regional scale. Multi-way partial least squares (N-PLS) regression was used as a supervised technique to predict the intensity of damage caused to vineyards by the heatwave phenomenon that impacted the vineyards in the south of France in 2019. The model was developed based on available ground truth data of yield losses for 107 vineyard blocks in the Languedoc-Roussillon region and multispectral time-series predictor data for the period May to August 2019. The model showed a performance accuracy (R2) of 0.56 in the calibration set and of 0.66 in the validation set, with a standard error of cross-validation in the calibration set of 12.4% and a standard error of the prediction of yield losses in the validation set of 10.7. The model was applied at a regional scale on 4978 vineyard blocks to predict yield losses using spectral and temporal attributes. The prediction of the yield loss due to heat stress at a regional scale was related to the spatial pattern of maximum temperatures recorded during the extreme weather event. This relation was confirmed by a chi-square test (p < 5%). The introduction of N-PLS insights into the analysis enables the characterisation of heat stress responses in vineyards and the identification of spectro-temporal profiles relevant for understanding the effects of heatwaves on vine blocks at a regional scale.

Chronotopes of security legal regimes

Legal regimes dealing with security have prominent temporal attributes: they are often intended to operate for a specified period of time in response to an imminent danger and allow governments to employ extraordinary measures enabling them to act faster when faced with time- critical scenarios. Such regimes also have prominent spatial attributes: they often protect a physical border, delineate spaces with extra-legal status, or use surveillance measures such as cameras or patrols for monitoring designated areas. Based on the analysis of one security regime that was imposed on the Palestinian minority in Israel between 1948 and 1966, I argue in this article that such spatial and temporal attributes affect each other and that different legal measures associated with security can be characterized by the specific time/space configuration – or chronotope – embedded in them. In Israel, a military regime was imposed on specific areas to foil the movement of its subjects and thereby further its territorial objectives. The procedures that the regime employed were therefore designed to monitor and control individuals’ whereabouts. Each of these seemingly spatial attributes, however, gained its particular function and meaning from a specific interaction with temporal attributes. The prism of the chronotope illuminates how security legal measures generate distinct modes of governance and produce different boundaries to the political community, in a way that a one-dimensional analysis fails to capture.

Sharing behavior in ride-hailing trips: A machine learning inference approach

Ride-hailing is rapidly changing urban and personal transportation. Ride sharing or pooling is important to mitigate negative externalities of ride-hailing such as increased congestion and environmental impacts. However, there lacks empirical evidence on what affect trip-level sharing behavior in ride-hailing. Using a novel dataset from all ride-hailing trips in Chicago in 2019, we show that the willingness of riders to request a shared ride has monotonically decreased from 27.0% to 12.8% throughout the year, while the trip volume and mileage have remained statistically unchanged. We find that the decline in sharing preference is due to an increased per-mile costs of shared trips and shifting shorter trips to solo. Using ensemble machine learning models, we find that the travel impedance variables (trip cost, distance, and duration) collectively contribute to 95% and 91% of the predictive power in determining whether a trip is requested to share and whether it is successfully shared, respectively. Spatial and temporal attributes, sociodemographic, built environment, and transit supply variables do not entail predictive power at the trip level in presence of these travel impedance variables. This implies that pricing signals are most effective to encourage riders to share their rides. Our findings shed light on sharing behavior in ride-hailing trips and can help devise strategies that increase shared ride-hailing, especially as the demand recovers from pandemic.