Click Patterns Research Articles

Building Advanced Web Applications Using Data Ingestion and Data Processing Tools

Today, advanced websites serve as robust data repositories that constantly collect various user-centered information and prepare it for subsequent processing. The data collected can include a wide range of important information from email addresses, usernames, and passwords to demographic information such as age, gender, and geographic location. User behavior metrics are also collected, including browsing history, click patterns, and time spent on pages, as well as different preferences like product selection, language preferences, and individual settings. Interactions, device information, transaction history, authentication data, communication logs, and various analytics and metrics contribute to the comprehensive range of user-centric information collected by websites. A method to systematically ingest and transfer such differently structured information to a central message broker is thoroughly described. In this context, a novel tool—Dataphos Publisher—for the creation of ready-to-digest data packages is presented. Data acquired from the message broker are employed for data quality analysis, storage, conversion, and downstream processing. A brief overview of the commonly used and freely available tools for data ingestion and processing is also provided.

Evidence from sperm whale clans of symbolic marking in non-human cultures

Culture, a pillar of the remarkable ecological success of humans, is increasingly recognized as a powerful force structuring nonhuman animal populations. A key gap between these two types of culture is quantitative evidence of symbolic markers-seemingly arbitrary traits that function as reliable indicators of cultural group membership to conspecifics. Using acoustic data collected from 23 Pacific Ocean locations, we provide quantitative evidence that certain sperm whale acoustic signals exhibit spatial patterns consistent with a symbolic marker function. Culture segments sperm whale populations into behaviorally distinct clans, which are defined based on dialects of stereotyped click patterns (codas). We classified 23,429 codas into types using contaminated mixture models and hierarchically clustered coda repertoires into seven clans based on similarities in coda usage; then we evaluated whether coda usage varied with geographic distance within clans or with spatial overlap between clans. Similarities in within-clan usage of both "identity codas" (coda types diagnostic of clan identity) and "nonidentity codas" (coda types used by multiple clans) decrease as space between repertoire recording locations increases. However, between-clan similarity in identity, but not nonidentity, coda usage decreases as clan spatial overlap increases. This matches expectations if sympatry is related to a measurable pressure to diversify to make cultural divisions sharper, thereby providing evidence that identity codas function as symbolic markers of clan identity. Our study provides quantitative evidence of arbitrary traits, resembling human ethnic markers, conveying cultural identity outside of humans, and highlights remarkable similarities in the distributions of human ethnolinguistic groups and sperm whale clans.

Multiple keywords management in sponsored search advertising with interrelated consumer clicks

Advertisers face difficult decisions when bidding on keywords in their search-engine campaigns. This paper provides guidance by empirically investigating the decisions of sponsored search advertisers, a search engine, and consumers across multiple keywords with different characteristics in a comprehensive manner. Specifically, we examine online retailers’ bidding patterns, the search engine’s rank decisions, and consumer click patterns for multiple interrelated keywords using simultaneous equations Tobit models with fixed effects. Our results show how advertiser bids, as well as consumer clicks, are interrelated across various keywords. Moreover, our optimization results suggest that advertisers can allocate advertising budgets more efficiently when the interrelationships among keywords are considered.

Trumpet sounds emitted by male sperm whales in the Mediterranean Sea

Sperm whale trumpets are sounds only occasionally documented, with a well recognisable and stereotyped acoustic arrangement. This study investigated the acoustic features of the trumpets and the context in which these sounds were recorded, using acoustic data collected over 22 years, in the Pelagos Sanctuary area (North-Western Mediterranean Sea). Analysed trumpets (n = 230), recorded at the beginning of a dive after the whale fluke-up, comprised a series of acoustic units organized in short sequences. Acoustic parameters were derived for the entire trumpet and for each distinguishable unit in a trumpet. Overall, trumpet durations and their initial frequencies were higher in recordings collected when multiple whales were visually or acoustically detected in the observation area. The identity of 68 whales was assessed through photo-identification, with 29 individuals producing trumpets within and between years. The variability of the acoustic parameters appeared to be higher within the same individuals rather than between different individuals, suggesting an individual plasticity in composing and arranging units in a trumpet. Different click patterns were observed before and after the trumpets, with more complex sequences when (1) other whales were visually/acoustically detected, and (2) individuals were in suitable foraging sites (i.e., canyon areas). Trumpets were commonly followed or preceded by click patterns suited for communication, such as codas and/or slow clicks. Significant relations between the trumpet emission and the male-only long-range communication click pattern (i.e. slow clicks) emerged, supporting the hypothesis that a trumpet is a sound emitted by maturing/mature males in feeding grounds. This study provides the first evidence that trumpets were conserved in the sperm whale acoustic repertoire at the decadal timescale, persisting across years and individuals in the same area. This persistence may be functionally specific to foraging activities performed by males in a well-established feeding area.

Toward Improving the Prediction Accuracy of Product Recommendation System Using Extreme Gradient Boosting and Encoding Approaches

With the spread of COVID-19, the “untact” culture in South Korea is expanding and customers are increasingly seeking for online services. A recommendation system serves as a decision-making indicator that helps users by suggesting items to be purchased in the future by exploring the symmetry between multiple user activity characteristics. A plethora of approaches are employed by the scientific community to design recommendation systems, including collaborative filtering, stereotyping, and content-based filtering, etc. The current paradigm of recommendation systems favors collaborative filtering due to its significant potential to closely capture the interest of a user as compared to other approaches. The collaborative filtering harnesses features like user-profile details, visited pages, and click information to determine the interest of a user, thereby recommending the items that are related to the user’s interest. The existing collaborative filtering approaches exploit implicit and explicit features and report either good classification or prediction outcome. These systems fail to exhibit good results for both measures at the same time. We believe that avoiding the recommendation of those items that have already been purchased could contribute to overcoming the said issue. In this study, we present a collaborative filtering-based algorithm to tackle big data of user with symmetric purchasing order and repetitive purchased products. The proposed algorithm relies on combining extreme gradient boosting machine learning architecture with word2vec mechanism to explore the purchased products based on the click patterns of users. Our algorithm improves the accuracy of predicting the relevant products to be recommended to the customers that are likely to be bought. The results are evaluated on the dataset that contains click-based features of users from an online shopping mall in Jeju Island, South Korea. We have evaluated Mean Absolute Error, Mean Square Error, and Root Mean Square Error for our proposed methodology and also other machine learning algorithms. Our proposed model generated the least error rate and enhanced the prediction accuracy of the recommendation system compared to other traditional approaches.

An Attention-Based Latent Information Extraction Network (ALIEN) for High-Order Feature Interactions

One of the primary tasks for commercial recommender systems is to predict the probabilities of users clicking items, e.g., advertisements, music and products. This is because such predictions have a decisive impact on profitability. The classic recommendation algorithm, collaborative filtering (CF), still plays a vital role in many industrial recommender systems. However, although straight CF is good at capturing similar users’ preferences for items based on their past interactions, it lacks regarding (1) modeling the influences of users’ sequential patterns from their individual history interaction sequences and (2) the relevance of users’ and items’ attributes. In this work, we developed an attention-based latent information extraction network (ALIEN) for click-through rate prediction, to integrate (1) implicit user similarity in terms of click patterns (analogous to CF), and (2) modeling the low and high-order feature interactions and (3) historical sequence information. The new model is based on the deep learning, which goes beyond the capabilities of econometric approaches, such as matrix factorization (MF) and k-means. In addition, the approach provides explainability to the recommendation by interpreting the contributions of different features and historical interactions. We have conducted experiments on real-world datasets that demonstrate considerable improvements over strong baselines.

How do online learners study? The psychometrics of students' clicking patterns in online courses.

College students’ study strategies were explored by tracking the ways they navigated the websites of two large (Ns of 1384 and 671) online introductory psychology courses. Students’ study patterns were measured analyzing the ways they clicked outside of the regularly scheduled class on study materials within the online Learning Management System. Three main effects emerged: studying course content materials (as opposed to course logistics materials) outside of class and higher grades are consistently correlated; studying at any time except in the late night/early morning hours was strongly correlated with grades; students with higher Scholastic Aptitude Test (SAT) scores made higher grades but accessed course materials at lower rates that those with lower SATs. Multiple regressions predicting grades using just SATs and click rates accounted for almost 43 and 36 percent of the grade variance for the Fall and Spring classes respectively. Implications for using click patterns to understand and shape student learning are discussed.

Relating Task Demand, Mental Effort and Task Difficulty with Physicians’ Performance during Interactions with Electronic Health Records (EHRs)

ABSTRACTObjective was to assess the relationship between task demand, mental effort, task difficulty, and performance during physicians’ interaction with electronic health records (EHRs). Seventeen physicians performed three EHR-based scenarios with varying task demands. Mental effort was measured using eye tracking measures via task evoked pupillary responses (TEPR), blink frequency, and gaze speed; task difficulty (or user behavior) was measured using frequent mouse click patterns and task flow; user performance was quantified using two types of omission errors: (i) omission errors with no evidence of trying to complete the task and (ii) omission error with evidence of trying but unable to complete the task. The results indicated that task demand significantly increased mental effort, but not task difficulty. Task demand, mental effort, and task difficulty all predicted performance. Specifically, there was a significant relationship between (i) task demand, TEPR and omission errors with no evidence of trying to complete the task, and (ii) blink frequency, repeated search clicks and omission error with evidence of trying but unable to complete the task. In concert, results suggest that physicians’ performance during EHR interaction was negatively affected by task demands and increase in mental effort. This highlight the need for implementation of appropriate quality assurance (QA) measures, in addition to EHR usability improvement, to minimize omission errors and improve physician’s performance. Additionally, the lack of relationship between task demand and task difficulty highlights a need for further methodological and empirical studies to advance our understanding from theory to application during physician–EHR interaction.

Mining Users’ Preference Similarities in E-commerce Systems Based on Webpage Navigation Logs

Mining users’ preference patterns in e-commerce systems is a fertile area for a great many application directions, such as shopping intention analysis, prediction and personalized recommendation. The web page navigation logs contain much potentially useful information, and provide opportunities for understanding the correlation between users’ browsing patterns and what they want to buy. In this article, we propose a web browsing history mining based user preference discovery method for e-commerce systems. First of all, a user-browsing-history-hierarchical-presentationgraph to established to model the web browsing histories of an individual in common e-commerce systems, and secondly an interested web page detection algorithm is designed to extract users’ preference. Finally, a new method called UPSAWBH (User Preference Similarity Calculation Algorithm Based on Web Browsing History), which measure the level of users’ preference similarity on the basis of their web page click patterns, is put forward. In the proposed UPSAWBH, we take two factors into account: 1) the number of shared web page click sequence, and 2) the property of the clicked web page that reflects users’ shopping preference in e-commerce systems. We conduct experiments on real dataset, which is extracted from the server of our self-developed e-commerce system. The results indicate a good effectiveness of the proposed approach.

A recommendation engine for travel products based on topic sequential patterns

Travel products recommendation has become one of emerging issues in the realm of recommendation systems. The widely-used collaborative filtering algorithms are usually difficult to be used for recommending travel products due to a number of reasons, including (1) the content of travel products is very complex, (2) the user-item matrix is extremely sparse, and (3) the cold-start users are widely existing. To tackle these issues, we try to exploit Web server logs for generating recommendation, and present a novel recommendation engine (SECT for short) for travel products based on topic sequential patterns. In detail, we first extract topics from semantic description of every Web page. Then, we mine topic frequent sequential patterns and their target products to form click patterns library. At last, we propose a Markov n-gram model for matching the real-time click-stream of users with the click patterns library and thus computing recommendation scores. Experimental results on a real-world travel dataset demonstrate that the SECT prevails over the state-of-art baseline algorithms. In particular, SECT shows merits in improving the both coverage and accuracy for recommending products to cold-start users. Also, SECT is effective to recommend long tail items and outperform baseline algorithms.

Recommender System Based on Product Taxonomy in E-Commerce Sites *

This article describes a novel and fast recommender system for websites based on product taxonomy and user click patterns. The proposed system consists of the following four steps. First, a product-preference matrix for each customer is estimated through a linear combination of the click, basket placement, and purchase statuses. Second, the preference matrix of the genre and that of the specific type are constructed by computing the ratios of the number of clicks, basket placements, and purchases of a product to the totals. Third, cluster analysis is performed using the genre preference matrix, and a neighborhood formation process is conducted using the specific-type preference matrix. Finally, data are generated for prediction, in which a customer's preference for specific types is greater than a given threshold value. Using these data sets, computational burden and processing time are greatly reduced. The effectiveness of the proposed approach was assessed by applying the F1 metric to an experimental e-commerce website. The proposed method outperformed conventional methods.

CLICK COMMUNICATION IN HARBOUR PORPOISES PHOCOENA PHOCOENA

ABSTRACT Sound plays an important role for toothed whales in foraging and communication. However, little is known about acoustic communication in the toothed whale species that only produce narrow band high frequency (NBHF) clicks, such as the harbour porpoise Phocoena phocoena. To study acoustic behaviour and to quantify the source parameters of porpoise communication signals, the acoustic and swimming behaviour of three adults and one calf were recorded using an array of hydrophones, acoustic tags and an overhead video camera. We tested the hypothesis that different behavioural interactions between porpoises involve specific click patterns for communication and measured the source characteristics of these click patterns to estimate the active space of porpoise click communication. Our results provide strong evidence that porpoises communicate acoustically using specific patterns of clicks with source properties comparable to normal echolocation clicks, and that they employ stereotyped aggressive click patterns, exposing conspecifics to received levels of up to 180 dB re 1 μPa (pp). The measured source properties render estimated active spaces of less than 1000 meters for porpoises' communication sounds. Compared to other cetaceans, porpoises must therefore remain much closer to be able to communicate acoustically.

Information architecture: Data‐driven design: Using web analytics to validate heuristics system

Information architecture: Data‐driven design: Using web analytics to validate heuristics system

Sound production by abdominal tymbal organs in two moth species: the green silver-line and the scarce silver-line (Noctuoidea: Nolidae: Chloephorinae).

Male moths of the chloephorine species Pseudoips prasinana and Bena bicolorana produce clicks (approximately 100 dB peSPL at 10 cm) using ventral tymbal organs located in a cleft in the second abdominal sternite. Large muscles insert on the dorsal part of the tymbal frame and rhythmically flex a thin sheet of cuticle. Normally, each sound-production cycle contains four clicks, the left and right tymbals producing clicks both on active buckling caused by muscle contraction and on the passive elastic return from buckling. Histochemical staining indicated the presence of elastic resilin-like proteins in the tymbals. Obvious differences between the click patterns of the two species reflect differences in their tymbal morphology. P. prasinana has smooth tymbals and produces a single click (300 µs, 40 kHz) for each tymbal buckling. In contrast, B. bicolorana has striae on the medial part of the tymbals. Accordingly, it produces many clicks per buckling. The click pattern is a heterogeneous mixture of large clicks at 52 kHz, resembling those of P. prasinana, interspersed with series of broad-band clicks (20-100 kHz) of lower intensity (15-20 dB). Thus, in chloephorine moths, there is a correlation between the structure and function of the smooth and striated tymbals that is strikingly similar to that in arctiid moths, although the two types of tymbals have evolved independently. The hearing of P. prasinana is tuned to its own sounds with lowest threshold (38 dB SPL) at 40-60 kHz. We suggest that sound production in male chloephorines plays a part in sexual acoustic communication.

THE CLICK‐SOUNDS OF NARWHALS (MONODON MONOCEROS) IN INGLEFIELD BAY, NORTHWEST GREENLAND

AbstractWe studied the sounds of narwhals (Monodon monoceros) foraging in the open waters in Northwest Greenland. We used a linear, vertical array of three hydrophones (depth 10 m, 30 m, 100 m) with a fourth hydrophone (depth 30 m) about 20 m from the vertical array. A smaller fifth hydrophone (depth 2 m) allowed for registering frequencies up to 125 kHz (± 2 dB) when signals were recorded at 762 mm/set on an instrumentation tape recorder. Clicks were the prevalent signals, but we heard whistles occasionally. We separated the clicks into two classes: click trains that had rates of 3‐10 clicks/sec and click bursts having rates of 110‐150 clicks/sec. The spectra of train clicks had maximum amplitudes at 48 ± 10 kHz and a duration of 29 ± 6 psec. The spectra of burst clicks had maximum amplitudes at 19 ± 1 kHz and a duration of 40 ± 3 psec. By analogy with other dolphin species, narwhals presumably use the clicks for echolocation during orientation and for locating prey. The narwhal click patterns resemble those of insectivorous bats. Click trains might correspond to bat searching signals and click bursts to the bat's terminal “buzz”, emitted just before prey capture.

Discrimination of auditory temporal patterns.

Two same-different discrimination experiments were performed for click patterns having a total duration of about 4 sec and interclick intervals of n x 250 msec, with n a random integer. In Experiment 1, the influence of the physical click group structure on discrimination performance was investigated. In Experiment 2, the effect of the strength of an induced internal clock on discrimination performance was measured. Performance was poor if the group structure of clicks was maintained during a change in click pattern and also if the induced internal clock strength was low. The performance of about 70% of the subjects improved significantly if either a change in click grouping structure occurred or a strong internal clock could be induced. These results cannot be accounted for with simple models based on single-interval duration discrimination or between-pattern correlation statistics.

Differences in echolocation click patterns of the beluga (D e l p h i n a p t e r u s l e u c a s) and the bottlenose dolphin (T u r s i o p s t r u n c a t u s)

In an echolocation experiment, the target detection performance of a beluga and a bottlenose dolphin were similar, but each produced different patterns of echolocation click trains. The beluga emitted three different patterns of echolocation clicks. A pattern I click train started with low-amplitude clicks, followed by packets of clicks. A packet contained several clicks with interclick intervals less than the two-way travel time to the target; the interpacket intervals were greater than the two-way travel time. A pattern II click train consisted of a combination of individual clicks, some with intervals less than and some greater than the two-way travel time. This pattern did not contain packets. The third pattern of click trains consisted of individual clicks with interclick intervals less than the two-way travel time. However, the bottlenose dolphin always emitted clicks with interclick intervals greater than the two-way travel time. These differences in click patterns suggest that the beluga has a different echolocation strategy than the bottlenose dolphin.

Cochlear responses to dynamic click patterns in the guinea pig.

Fast cochlear adaptation, expressed as percent inhibition of the summed action potential, is studied from the guinea pig cochlea responses to click trains, ramps, and steps in both directions. The transition time function of adaptation to constant click trains does not depend on click strength, but rather on click interval. On the background of steady state adaptation, click steps produce only transient changes of the adaptive state, opposite to step direction. Compared to constant train stimulation, adaptation is enhanced by descending click ramps, and diminished or reversed (near threshold) by ascending ramps.

Sperm whale codas

Short series of 3 to 40 or more clicks are produced by sperm whales, Physeter catodon, in stereotyped repetitive sequences or codas. The temporal click patterns in codas appear to be unique to individual whales over at least a few hours. It is suggested that sperm whale codas serve as a means of individual acoustic identification. An apparent exchange of codas between two animals was analyzed and acoustical locations calculated for the four-hydrophone array data that changes in underwater meovement coincided with changes in the coda sequences.