Detection Of Behavioral Patterns Research Articles

From Movement to Meaning: Real-time Detection of Behavioural Patterns in Human Psychology using Deep Learning and Time Series Sequence

Understanding human behaviour and psychology is complex and involves various fields, including cognitive science, neurology, and artificial intelligence (AI). In this study, we introduce a cutting-edge system that detects both manual (like hand gestures) and non-manual (such as facial expressions or body movements) features in real time, using advanced deep learning techniques and time-series analysis. This system translates these human movements into text, providing a powerful tool to analyse subtle behavioural and psychological signals. By processing real-time data, our system significantly advances psychology by detecting small expressions, involuntary gestures, and behaviour patterns often associated with psychological and neurological conditions. For instance, it can help identify repetitive actions or atypical gestures in people with autism spectrum disorder (ASD), which are critical for early diagnosis. It can also track signs of neurodegenerative diseases like Parkinson’s or Alzheimer’s, detecting tremors, posture changes, or facial expressions, and offer insights for early intervention

An Effective Yak Behavior Classification Model with Improved YOLO-Pose Network Using Yak Skeleton Key Points Images

Yak behavior is a valuable indicator of their welfare and health. Information about important statuses, including fattening, reproductive health, and diseases, can be reflected and monitored through several indicative behavior patterns. In this study, an improved YOLOv7-pose model was developed to detect six yak behavior patterns in real time using labeled yak key-point images. The model was trained using labeled key-point image data of six behavior patterns including walking, feeding, standing, lying, mounting, and eliminative behaviors collected from seventeen 18-month-old yaks for two weeks. There were another four YOLOv7-pose series models trained as comparison methods for yak behavior pattern detection. The improved YOLOv7-pose model achieved the best detection performance with precision, recall, mAP0.5, and mAP0.5:0.95 of 89.9%, 87.7%, 90.4%, and 76.7%, respectively. The limitation of this study is that the YOLOv7-pose model detected behaviors under complex conditions, such as scene variation, subtle leg postures, and different light conditions, with relatively lower precision, which impacts its detection performance. Future developments in yak behavior pattern detection will amplify the simple size of the dataset and will utilize data streams like optical and video streams for real-time yak monitoring. Additionally, the model will be deployed on edge computing devices for large-scale agricultural applications.

A Road Behavior Pattern-Detection Model in Querétaro City Streets by the Use of Shape Descriptors

In this research, a proposed model aims to automatically identify patterns of spatial and temporal behavior of moving objects in video sequences. The moving objects are analyzed and characterized based on their shape and observable attributes in displacement. To quantify the moving objects over time and form a homogeneous database, a set of shape descriptors is introduced. Geometric measurements of shape, contrast, and connectedness are used to represent each moving object. The proposal uses Granger’s theory to find causal relationships from the history of each moving object stored in a database. The model is tested in two scenarios; the first is a public database, and the second scenario uses a proprietary database from a real scenario. The results show an average accuracy value of 78% in the detection of atypical behaviors in positive and negative dependence relationships.

Relationship between children's eating behavior (1-6years) and body mass index: a cross-sectional study in French maternal-infant protection centers within the Parisian region.

Early detection of obesity-promoting dietary behavior patterns improves the identification of at-risk families and the implementation of interventions. This is accomplished through the use of the Child Eating Behavior Questionnaire (CEBQ). No study has been conducted using the CEBQ in children followed in Essonne's Maternal-Infant Protection (PMI) centers. We investigated, in a cross-sectional design, the differences in children's eating behavior with PMI follow-up according to their weight status. A questionnaire addressed to parents was collected in PMI centers. Multiple hierarchical regression analysis was used to investigate the predictability of the child's CEBQ on body mass index (BMI). From January to April 2022, 850 children were selected, from which 500 (aged 1-6years) were included, and of whom 10.6% were obese. There was a significant positive association between 'Food Responsiveness', 'Enjoyment of Food' and BMI. In contrast, there was a significant negative association between 'Satiety Responsiveness', 'Slowness in Eating' and BMI. Besides, 'Food approach' and 'food avoidance' behaviors were positively and negatively related to BMI z-scores, respectively. Due to significant differences in children's eating behavior according to their weight, it is needed to raise awareness among parents about their impact on them.

Graph deep learning recognition of port ship behavior patterns from a network approach

The detection and recognition of ship mobile behavior patterns based on automatic identification system (AIS) data are crucial for ship navigation and maritime supervision. However, present methods, such as rule-based constraints and density clustering extraction, still suffer from restrictions imposed by artificial settings of parameters and thresholds. The lack of neighborhood context information in unstructured and serialized ship trajectory vector data makes it challenging to incorporate advanced methods such as deep learning for pattern learning. This study builds multiple semi-supervised deep learning graph neural network (GNN) models based on the message passing paradigm for recognizing ship mobile behavior patterns by constructing an AIS trajectory network and computing multi-order node features through Delaunay triangulation. It can get rid of the dependence on parameters of traditional rule-based and unsupervised learning methods. It also reduces the dependence on auxiliary information in trajectory qualitative by introducing multi-order node features. We conducted the experiments on cargo ship data from New York and Singapore to test our method. The model's classification accuracy is more than 99% for the New York dataset and more than 95% for the Singapore dataset. This method can be extended to other types of ships and traffic trajectory vector data with the excellent application potential of GNN in pattern recognition of vector mobile data. The code and experimental data are available at: https://github.com/destiny1103/DT-GNN.

An automated group-housed oral fentanyl self-administration method in mice.

Social factors play a critical role in human drug addiction, and humans often consume drugs together with their peers. In contrast, in traditional animal models of addiction, rodents consume or self-administer the drug in their homecage or operant self-administration chambers while isolated from their peers. Here, we describe HOMECAGE ("Home-cage Observation and Measurement for Experimental Control and Analysis in a Group-housed Environment"), a translationally relevant method for studying oral opioid self-administration in mice. This setting reduces experimental confounds introduced by social isolation or interaction with the experimenter. We have developed HOMECAGE, a method in which mice are group-housed and individually monitored for their consumption of a drug vs. a reference liquid. Mice in HOMECAGE preserve naturalistic aspects of behavior, including social interactions and circadian activity. The mice showed a preference for fentanyl and escalated their fentanyl intake over time. Mice preferred to consume fentanyl in bouts during the dark cycle. Mice entrained to the reinforcement schedule of the task, optimizing their pokes to obtain fentanyl rewards, and maintained responding for fentanyl under a progressive ratio schedule. HOMECAGE also enabled the detection of cage-specific and individual-specific behavior patterns and allowed the identification of differences in fentanyl consumption between co-housed control and experimental mice. HOMECAGE serves as a valuable procedure for translationally relevant studies on oral opioid intake under conditions that more closely mimic the human condition. The method enables naturalistic investigation of factors contributing to opioid addiction-related behaviors and can be used to identify novel treatments.

Real-time classification of cattle behavior using Wireless Sensor Networks

The detection of activity and behavioral patterns using accelerometers in humans has been a longstanding research. Progress in this field has been successfully transferred to the study of animal behavior thanks to the emergence of new Internet of Things (IoT) technologies such as Wireless Sensor Networks (WSNs) and the need for more complex behavioral information. All the systems proposed by the scientific community have been evaluated in terms of classification performance. However, not many studies consider the potential loss of accuracy undergone when these systems are deployed in WSNs, given the low computational capacities of their nodes and the need for a low energy consumption. This paper proposes a behavioral pattern classification system for four types of animal behavior in free-range grazing cattle along with an optimal and a restricted configuration thereof. The evaluation of this system takes into account its classification performance and its expected accuracy under the limited resources that WSNs can offer. The results show that the optimal configuration improves the performance of its alternatives by an average of 9% and the restricted configuration by an average of 6%. Moreover, as part of a WSN, the results demonstrate a flawless accuracy in the optimal and restricted configurations for walking (100% and 100%), almost perfect for grazing (98.39% and 98.59%), and acceptable for lying (79.03% and 69.01%) and standing (75.81% and 70.42%). In conclusion, the proposed system represents a powerful tool for analyzing complex behaviors in cattle through the use of WSNs.

USING A VIRTUAL TWIN OF A BUILDING TO ENSURE SECURITY IN EDUCATIONAL INSTITUTIONS

This research paper delves into the exploration of computer vision technology and digital twins as a means to enhance security measures in educational institutions. The study primarily focuses on the creation of a virtual replica of the first floor of a school and the integration of a person detection algorithm with the existing surveillance cameras. By leverag- ing the capabilities of the digital twin and real-time monitoring, comprehensive surveillance of the premises becomes feasible, resulting in simplified security operations. The paper sheds light on the significant potential of training neural networks for specific security tasks, such as the identification of weapons or the detection of anomalies in human behavior. These trained neural networks can be seamlessly integrated into the digital twin, thus ensuring public safety within the educational environment. The findings of this study provide substantial evidence for the effectiveness of computer vision technology and digital twins in bolstering security measures. The ability to create a virtual representation of the school’s first floor enables com- prehensive monitoring and surveillance, aiding in the prevention and prompt response to se- curity incidents. The integration of person detection algorithms further enhances the system’s capabilities by automatically identifying and tracking individuals within the premises. Addi- tionally, the deployment of neural networks for specialized security tasks adds an extra layer of protection, enabling the identification of potential threats and the detection of abnormal behavior patterns. By employing computer vision technology and digital twins, educational institutions can establish an advanced security infrastructure that optimizes monitoring, en- hances situational awareness, and ensures a safer environment for students, staff, and visitors. The research presented in this paper highlights the tremendous potential and practical impli- cations of these technologies in the realm of educational security.

Comparative performance analysis of three machine learning algorithms applied to sensor data registered by a leg-attached accelerometer to predict metritis events in dairy cattle

Routinely collected sensor data could be used in metritis predictive modeling but a better understanding of its potential is needed. Our objectives were 1) to compare the performance of k-nearest neighbors (k-NN), random forest (RF), and support vector machine (SVM) classifiers on the detection of behavioral patterns associated with metritis events measured by a leg-attached accelerometer (TrackaCow, ENGS, Hampshire, UK); 2) to study the impact of farm scheduled activities on model performance; and 3) to identify which behaviors yield the highest F1 score for metritis prediction as a function of the number of time window and time-lags. A total of 239 metritis events (188 non-metritis and 51 metritis events) were retrospectively created based on changes in two consecutive uterine evaluations from a dataset containing sensor and clinical data during the first 21 days postpartum between June 2014 and May 2017. These events were associated with a total of 10,874 - 14,138 data points corresponding to hourly measurements of lying time, lying bouts, steps, intake, and intake visits. Sensor data corresponding to the 3 days before each metritis event were aggregated every 24-, 12-, 6-, and 3-hour time windows. Multiple time-lags were also used to determine the optimal number of past observations needed for optimal classification. Similarly, different decision thresholds were compared. Depending on the classifier, algorithm hyperparameters were optimized using grid search (RF, k-NN, SVM) and random search (RF). All behaviors changed throughout the study period and showed distinct daily patterns. From the three algorithms, RF had the highest F1 score, with no impact of scheduled farm activities on classifier performance. Furthermore, 3- and 6-hour time windows had the best balance between F1 scores and number of time-lags. We concluded that steps and lying time can be used to predict metritis using data from 2 to 3 days before a metritis event. Findings from this study will be used to develop more complex prediction models that could identify cows at higher risk of experiencing metritis.

Impact of sensor data pre-processing strategies and selection of machine learning algorithm on the prediction of metritis events in dairy cattle

With all the sensor data currently generated at high frequency in dairy farms, there is potential for earlier diagnosis of postpartum diseases compared with traditional monitoring methodologies. Our objectives were 1) to compare the impact of sensor data pre-processing on classifier performance by using multiple time windows before a given metritis event, while considering other cow-level factors and farm-scheduled activities; 2) to compare the performance of random forest (RF), k-nearest neighbors (k-NN), and support vector machine (SVM) classifiers at different decision thresholds using different number of past observations (time-lags) for the detection of behavioral patterns associated with changes in metritis scores; and 3) to compare classifier performance between each one of the five behaviors registered every hour by an ear-tag 3-axis accelerometer (CowManager, Agis Autimatisering, Harmelen, Netherlands). A total of 239 metritis events were created by comparing metritis scores between two consecutive clinical evaluations from cows that were retrospectively selected from a dataset containing sensor data and health information during the first 21 days postpartum from June 2014 to May 2017. Hourly sensor data classified by the accelerometer as either ruminating, eating, not active (including both standing or lying), and two different levels of activity (active and high activity) behaviors corresponding to the 3 days before each metritis event were aggregated every 24-, 12-, 6-, and 3-hour time windows. Multiple time-lags were also used to determine the optimal number of past observations needed for optimal classification. Similarly, different decision thresholds were compared in terms of model performance. Depending on the classifier, algorithm hyperparameters were optimized using grid search (RF, k-NN, SVM) and random search (RF). All behaviors changed throughout the study period and showed distinct daily patterns. From the three algorithms, RF had the highest F1 score followed by k-NN and SVM. Furthermore, sensor data aggregated every 6- or 12-h time windows had the best model performance at multiple time-lags. We concluded that the data from the first 3 days post-partum should be discarded when studying metritis, and either one of the five behaviors measured with CowManager could be used when predicting metritis when sensor data were aggregated every 6- or 12-hour time windows, and using time-lags corresponding to 2–3 days before a given event, depending on the time window used. This study shows how to maximize sensor data in their potential for disease prediction, enhancing the performance of algorithms used in machine learning.

Can we detect patterns in behavioral time series of cows using cluster analysis?

Time series analysis can facilitate the detection of complex behavioral patterns and potentially provide new opportunities to assess animal welfare. The aim was to investigate whether dairy cows exhibit daily, individual patterns in activity and in area use in the barn. We predicted that behavioral patterns will be more consistent (1) within than between cows, (2) when area categorization is more specific and, thus, allows the detection of individual preferences for areas, and (3) during the night. We conducted the study at an experimental farm with 20 lactating Brown Swiss and Swiss Fleckvieh cows. The animals were housed in cubicles, and they received feed and were milked twice daily. Activity was recorded with IceTag pedometers (IceRobotics Ltd.), and area use with the SMARTBOW sensor system (Zoetis). Data were collected for 55 consecutive days and analyzed at 1-min intervals. To investigate the behavioral time series, we performed a hierarchical clustering analysis. A clustering process calculated distances between days, which were compared within and between cows based on t-tests and analyses of variance. Dendrograms of activity and area use showed that days of individual cows could not be grouped more closely together than those of different cows. A slightly better grouping was achieved with a more specific area categorization, but not during a specific time period. However, the average distances between days were always smaller within (mean ± SD; activity: 95.62 ± 76.88, lying areas: 0.14 ± 0.03, functional areas: 0.12 ± 0.01) than between cows (activity: 109.62 ± 75.33, lying areas: 0.16 ± 0.02, functional areas 0.13 ± 0.01). Considering that the time series of individual cows were slightly but always more similar compared with those between cows, and that more consistent patterns were found when the area categorization was more specific, it can be concluded that the cows exhibited weak individual preferences in area use and also weak daily individual patterns in activity and area use. Because the visual exploratory and empirical approaches used in this study do not account for variability, they do not seem to be suitable for the detection of patterns in animals that display greater plasticity in their temporal structure of activity. Thus, although determining the temporal structure of activity and area use bears the potential to assess the behavior and, in turn, for example, the physiological state and health status of cows, it does not seem to be achievable with a cluster analysis. Therefore, time series methods that account for temporal fluctuations in behavior should be further explored.

Securing electronic health records against insider-threats: A supervised machine learning approach

The introduction of electronic health records (EHR) has created new opportunities for efficient patient data management. For example, preventative medical practice, rather than reactive, is possible through the integration of machine learning to mine digital patient record datasets. Furthermore, within the wider smart cities’ infrastructure, EHR has considerable environmental and cost-saving benefits for healthcare providers. Yet, there are inherent dangers to digitising patient records. Considering the sensitive nature of the data, EHR is equally at risk of both external threats and insider attacks, but security applications are predominantly facing the outer boundary of the network. Therefore, in this work, the focus is on insider data misuse detection. The approach involves the use of supervised classification (decision tree, random forest and support vector machine) based off pre-labelled real-world data collated from a UK-based hospital for the detection of EHR data misuse. The results demonstrate that by employing a machine learning approach to analyse EHR data access, anomaly detection can be achieved with a 0.9896 accuracy from a test set and 0.9908 from the validation set using a support vector machine classifier. The emphasis of this research is on the detection of EHR data misuse, through the detection of anomalous behavioural patterns. Based on the results, the recommendation is to adopt an SVM for data misuse/insider threat detection.

A systematic survey of data mining and big data in human behavior analysis: Current datasets and models

AbstractIn recent years, understanding human behavior has become one of the most important topics in the field of computer vision research. The reason for this growing attention is the wide range of applications that can benefit from the results of this field of research. The human behavior analysis (HBA) includes a wide range of research areas from the detection of human motion and action. Datasets created through actions and detection of human activities make it possible to compare different detection methods with the same input data. Data mining and big data approaches are very popular for analyzing data related to human behavior and can be used to address the challenges of fast processing. This article provides a systematic survey of data mining and big data in the HBA. We focus on current datasets and models related to the detection of human behavior patterns in the literature. The purpose of this survey is to assist researchers in select appropriate datasets and models to evaluate algorithms, as well as to identify research gaps for future work. To achieve this goal, articles published between 2010 and 2021 have been reviewed. These articles fall into five general categories in terms of dataset focus: object detection, motion, action, activity, and behavior. This article provides a summary of data mining and big data models in the HBA, as well as related datasets based on these categories, to highlight promising research avenues for future work.

Detection of Behavioral Patterns Employing a Hybrid Approach of Computational Techniques

As far as the present state is concerned in detecting the behavioral pattern of humans (subject) using morphological image processing, a considerable portion of the study has been conducted utilizing frontal vision data of human faces. The present research work had used a side vision of human-face data to develop a theoretical framework via a hybrid analytical model approach. In this example, hybridization includes an artificial neural network (ANN) with a genetic algorithm (GA). We researched the geometrical properties extracted from side-vision human-face data. An additional study was conducted to determine the ideal number of geometrical characteristics to pick while clustering. The close vicinity of minimum distance measurements is done for these clusters, mapped for proper classification and decision process of behavioral pattern. To identify the data acquired, support vector machines and artificial neural networks are utilized. A method known as an adaptive-unidirectional associative memory (AUTAM) was used to map one side of a human face to the other side of the same subject. The behavioral pattern has been detected based on two-class problem classification, and the decision process has been done using a genetic algorithm with best-fit measurements. The developed algorithm in the present work has been tested by considering a dataset of 100 subjects and tested using standard databases like FERET, Multi-PIE, Yale Face database, RTR, CASIA, etc. The complexity measures have also been calculated under worst-case and best-case situations.

Visual analytics of sensor movement data for cheetah behaviour analysis

Current tracking technology such as GPS data loggers allows biologists to remotely collect large amounts of movement data for a large variety of species. Extending, and often replacing interpretation based on observation, the analysis of the collected data supports research on animal behaviour, on impact factors such as climate change and human intervention on the globe, as well as on conservation programs. However, this analysis is difficult, due to the nature of the research questions and the complexity of the data sets. It requires both automated analysis, for example, for the detection of behavioural patterns, and human inspection, for example, for interpretation, inclusion of previous knowledge, and for conclusions on future actions and decision making. For this analysis and inspection, the movement data needs to be put into the context of environmental data, which helps to interpret the behaviour. Thus, a major challenge is to design and develop methods and intuitive interfaces that integrate the data for analysis by biologists. We present a concept and implementation for the visual analysis of cheetah movement data in a web-based fashion that allows usage both in the field and in office environments.Graphic abstract

La influencia del sexo en el uso de los campus virtuales. Estudio de caso

A comparative analysis has been carried out in order to study the similarities and differences in the use and management of space and time by students, based on their gender. The study analyses the data records generated by students from three different degree courses in two universities, throughout four academic years. The methodology includes exploratory statistical analysis and learning analytics for the detection of spatial, temporal and behavioural patterns. Results show a consistent convergence in most cases, although they also show marginal behavioral trends, both for the days of the week, the hours of the day, and for the different contents of the virtual campuses. This is more evident in its spatial aspect, which highlights some clear differences in the processes of distribution and concentration of the events under study: at least in this case, women do not act in the same way as men. Ultimately, the study proposes new forms of synergy between educational work and the application of the Social Sciences’ disciplinary contents thus strengthening the transfer of knowledge from specific didactics on both educational curriculum and teacher training.

An approach to support the construction of adaptive Web applications

Purpose This paper aims to presents Real-time Usage Mining (RUM), an approach that exploits the rich information provided by client logs to support the construction of adaptive Web applications. The main goal of RUM is to provide useful information about the behavior of users that are currently browsing a Web application. By consuming this information, the application is able to adapt its user interface in real-time to enhance the user experience. RUM provides two types of services as follows: support for the detection of struggling users; and user profiling based on the detection of behavior patterns. Design/methodology/approach RUM leverages the previous study on usability evaluation to provide a service that evaluates the usability of tasks performed by users while they browse applications. This evaluation is based on a metric that allows the detection of struggling users, making it possible to identify these users as soon as few logs from their interaction are processed. RUM also exploits log mining techniques to detect usage patterns, which are then associated with user profiles previously defined by the application specialist. After associating usage patterns to user profiles, RUM is able to classify users as they browse applications, allowing the application developer to tailor the user interface according to the users’ needs and preferences. Findings The proposed approach was exploited to improve user experience in real-world Web applications. Experiments showed that RUM was effective to provide support for struggling users to complete tasks. Moreover, it was also effective to detect usage patterns and associate them with user profiles. Originality/value Although the literature reports studies that explore client logs to support both the detection of struggling users and the user profiling based on usage patterns, no existing solutions provide support for detecting users from specific profiles or struggling users, in real-time, while they are browsing Web applications. RUM also provides a toolkit that allows the approach to be easily deployed in any Web application.

Temporal Saliency-Based Suspicious Behavior Pattern Detection

The topic of suspicious behavior detection has been one of the most emergent research themes in computer vision, video analysis, and monitoring. Due to the huge number of CCTV (closed-circuit television) systems, it is not easy for people to manually identify CCTV for suspicious motion monitoring. This paper is concerned with an automatic suspicious behavior detection method using a CCTV video stream. Observers generally focus their attention on behaviors that vary in terms of magnitude or gradient of motion and behave differently in rules of motion with other objects. Based on these facts, the proposed method detected suspicious behavior with a temporal saliency map by combining the moving reactivity features of motion magnitude and gradient extracted by optical flow. It has been tested on various video clips that contain suspicious behavior. The experimental results show that the performance of the proposed method is good at detecting the six designated types of suspicious behavior examined: sudden running, colliding, falling, jumping, fighting, and slipping. The proposed method achieved an average accuracy of 93.89%, a precision of 96.21% and a recall of 94.90%.

A Bayesian approach for the analysis of error rate studies in forensic science

Over the past decade, the field of forensic science has received recommendations from the National Research Council of the U.S. National Academy of Sciences, the U.S. National Institute of Standards and Technology, and the U.S. President's Council of Advisors on Science and Technology to study the validity and reliability of forensic analyses. More specifically, these committees recommend estimation of the rates of occurrence of erroneous conclusions drawn from forensic analyses. “Black box” studies for the various subjective feature-based comparison methods are intended for this purpose.In general, “black box” studies often have unbalanced designs, comparisons that are not independent, and missing data. These aspects pose difficulty in the analysis of the results and are often ignored. Instead, interpretation of the data relies on methods that assume independence between observations and a balanced experiment. Furthermore, all of these projects are interpreted within the frequentist framework and result in point estimates associated with confidence intervals that are confusing to communicate and understand.We propose to use an existing likelihood-free Bayesian inference method, called Approximate Bayesian Computation (ABC), that is capable of handling unbalanced designs, dependencies among the observations, and missing data. ABC allows for studying the parameters of interest without recourse to incoherent and misleading measures of uncertainty such as confidence intervals. By taking into account information from all decision categories for a given examiner and information from the population of examiners, our method also allows for quantifying the risk of error for the given examiner, even when no error has been recorded for that examiner. This opens the door to the detection of behavioural patterns in the decision-making of examiners through their ABC rate estimates. These patterns could be used to detect error prone examiners, enabling additional training efforts to be more tailored to each examiner, limiting the risk of errors before they occur.We illustrate our proposed method by reanalysing the results of the “Noblis Black Box” study by Ulery et al. [18]. We did not choose this study because we disagree with their results, but because it is a good example of a study with dependent observations and missing data, and the data is publicly available. The ABC estimates for the population generally agreed with Ulery et al.’s plug-in estimates. However, credible intervals obtained from ABC are much wider than the confidence intervals for the corresponding parameter estimates that did not account for the dependencies among observations.

A systematic meta-Review and analysis of learning analytics research

ABSTRACT As an emerging field of research, learning analytics (LA) offers practitioners and researchers information about educational data that is helpful for supporting decisions in management of teaching and learning. While often combined with educational data mining (EDM), crucial distinctions exist for LA that mandate a separate review. This study aims to conduct a systematic meta-review of LA for mining key information that could assist in describing new and helpful directions to this field of inquiry. Within 901 LA articles analyzed, eight reviews were identified and synthesised to identify and determine consistencies and gaps. Results show that LA is at the stage of early majority and has attracted great research efforts from other fields. The majority of LA publications were focused on proposing LA concepts or frameworks and conducting proof-of-concept analysis rather than conducting actual data analysis. Collecting small datasets for LA research is predominant, especially in K-12 field. Finally, four major LA research topics, including prediction of performance, decision support for teachers and learners, detection of behavioural patterns & learner modelling and dropout prediction, were identified and discussed deeply. The future research of LA is also outlined for purpose of better understanding and optimising learning as well as learning contexts.