Mixed Information Flow for Cross-Domain Sequential Recommendations

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of behavioral information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a mixed information flow network for cross-domain sequential recommendation to consider both the flow of behavioral information and the flow of knowledge by incorporating a behavior transfer unit and a knowledge transfer unit . The proposed mixed information flow network is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed mixed information flow network is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of mixed information flow network s to a scenario with two domains, but the method can easily be extended to multiple domains.

Fine Detection of Human Motion During Activities of Daily Living as a Clinical Indicator for the Detection and Early Treatment of Chronic Diseases: The E-Mob Project

Methods to measure physical activity and sedentary behaviors typically quantify the amount of time devoted to these activities. Among patients with chronic diseases, these methods can provide interesting behavioral information, but generally do not capture detailed body motion and fine movement behaviors. Fine detection of motion may provide additional information about functional decline that is of clinical interest in chronic diseases. This perspective paper highlights the need for more developed and sophisticated tools to better identify and track the decomposition, structuration, and sequencing of the daily movements of humans. The primary goal is to provide a reliable and useful clinical diagnostic and predictive indicator of the stage and evolution of chronic diseases, in order to prevent related comorbidities and complications among patients.

A review of the Larainae of Australia with description of seven new species and the new genus Australara (Coleoptera, Byrrhoidea, Elmidae)

The three genera and four species of Larainae (Elmidae) previously described from Australia are reviewed, and one new genus and seven new species are described: Australara glaisterigen. et sp. nov., Ovolara lawrenceisp. nov., Ovolara monteithisp. nov., Stetholus carinatussp. nov., Stetholus longipennissp. nov., Stetholus metatibialissp. nov., and Stetholus woronorasp. nov. A lectotype is designated for Hydora laticeps (Carter & Zeck), and the first new collection records of the species are reported since its description in 1932. The occurrence in Australia of Potamophilinus papuanus Satô, described from Papua New Guinea, is reported. A key to the species, photographic images of the external morphology and male genitalia, distribution maps, and habitat and behavioral information, when known, are provided for all twelve species of Australian Larainae.

Biased memory retrieval in the service of shared reality with an audience: The role of cognitive accessibility

After communicators have tuned a message about a target person’s behaviors to their audience’s attitude, their recall of the target’s behaviors is often evaluatively consistent with their audience’s attitude. This audience-tuning effect on recall has been explained as resulting from the communicators’ creation of a shared reality with the audience, which helps communicators to achieve epistemic needs for confident judgments and knowledge. Drawing on the ROAR (Relevance Of A Representation) model, we argue that shared reality increases the cognitive accessibility of information consistent (vs. inconsistent) with the audience’s attitude, due to enhanced truth relevance of this information. We tested this prediction with a novel reaction-time task in three experiments employing the saying-is-believing paradigm. Faster reactions to audience-consistent (vs. audience-inconsistent) information were found for trait information but not for behavioral information. Thus, audience-congruent accessibility bias emerged at the level at which impressions and judgments of other persons are typically organized. Consistent with a shared-reality account, the audience-consistent accessibility bias was correlated with perceived shared reality about the target person and with epistemic trust in the audience. Among possible explanations, the findings are best reconciled with the view that the creation of shared reality with an audience triggers basic and "automatic" (spontaneous, low-level) cognitive mechanisms that facilitate the retrieval of audience-congruent (vs. audience-incongruent) trait information about a target person.

The behavior propagation and confrontation competition model based on information energy

In recent years, the influence of group behavior on individual behavior has been widely concerned by people. This paper takes the propagation of behavior-related information as the influencing medium, constructs the behavior propagation and confrontation competition model based on information energy, and studies the propagation of single behavior and confrontation behaviors in the network. In the model, the behavioral information energy on nodes is related to the information edge weight and the length of the reachable path between nodes, and we quantify the propagation probability of behaviors and the competition probability between the confrontation behaviors by the behavioral information energy. Through modeling and analyzing the change of node motivation and the behavior propagation rule, we carry out the simulation in small-world network and BA scale-free network, respectively. Experimental results show that the information energy has a promoting effect on the propagation of behaviors, and the behaviors that erupt in the network generally have an important information dissemination basis in the early stage and may be promoted by relevant information in the later stage. An open and tightly connected network environment is easier to promote the large-scale propagation of a new behavior. In addition, when two kinds of confrontation behaviors occur in the crowd network, the propagation of behavior-related information and the maintenance of people’s interest in the behavior are the key to the success of the behavioral competition.

Relinquishing Owners Underestimate Their Dog's Behavioral Problems: Deception or Lack of Knowledge?

Undesirable behavior is a leading cause of canine relinquishment. Relinquishing owners could provide valuable information about their dog's behavior, although the reliability of their reports has been questioned by the sheltering community. This study aimed to investigate (a) whether relinquishing owners' reports of dog behavior differed based on the behavioral screening method; (b) whether relinquishing owners' reports were impacted by the confidentiality of their responses; and (c) whether relinquishing and non-relinquishing owners perceived the behavior of their dogs differently. The sample included 427 relinquished dogs from three animal shelters and 427 pet dogs, matched for sex and breed. Owners responded to a direct question about whether they were experiencing problems with their dog's behavior and completed the mini C-BARQ which includes 42 questions about the frequency and severity of specific canine behaviors in various circumstances. More than two-thirds (69.3%) of relinquishing owners indicated they were not experiencing problems with their dog's behavior when asked directly, compared with only 34.5% of pet owners. Yet, relinquished dogs had significantly higher (less desirable) scores than pet dogs across most C-BARQ scales. The disparity between C-BARQ scores and the single, direct question does not appear to be the result of deliberately biased reporting by relinquishing owners as the perceived confidentiality (or lack thereof) did not affect their responses (X2 = 1.44, p = 0.97). It is possible that relinquishing owners had less understanding of dog behavior and did not recognize behavior problems as a problem. Our findings support the use of standardized behavioral questionnaires, such as the mini C-BARQ, to collect behavioral information from owners at the time of relinquishment and highlight opportunities for animal shelters to reduce relinquishment by assisting owners to recognize and manage behavioral problems.

Fine Detection of Human Motion During Activities of Daily Living as a Clinical Indicator for the Detection and Early Treatment of Chronic Diseases: The E-Mob Project (Preprint)

UNSTRUCTURED Methods to measure physical activity and sedentary behaviors typically quantify the amount of time devoted to these activities. Among patients with chronic diseases, these methods can provide interesting behavioral information, but generally do not capture detailed body motion and fine movement behaviors. Fine detection of motion may provide additional information about functional decline that is of clinical interest in chronic diseases. This perspective paper highlights the need for more developed and sophisticated tools to better identify and track the decomposition, structuration, and sequencing of the daily movements of humans. The primary goal is to provide a reliable and useful clinical diagnostic and predictive indicator of the stage and evolution of chronic diseases, in order to prevent related comorbidities and complications among patients.

Improving learning and writing outcomes: Influence of cognitive and behavioral group awareness tools in wikis

Group awareness (GA) tools can facilitate learning processes and outcomes by visualizing different social attributes, such as cognitive and behavioral information about group members. To assist learning and writing in social media, combining various types of awareness information may foster learning processes due to challenges, which are difficult to address by one type of GA information alone. The systematic investigation of GA tool combinations is largely unexplored with GA information often being examined separately or intermixed. To reveal both positive and negative (interaction) effects of providing different types of GA information, we conducted a 2 × 2 between-subjects experiment with N = 158 participants. Learners were provided with a wiki learning environment and, except for the control condition, different types of GA tools involving cognitive (knowledge bars) and/or behavioral (participation bars) GA information. GA tool effects were considered at wiki selection, discussion, and article levels. Eye-tracking was used for investigating the attentional effect of the GA visualizations. The results show that both types of GA information have effects on individuals’ selection preference, more strongly with the goal to learn new content than to support other wiki collaborators, which were introduced as within goal scenarios. Also, participants provided with behavioral GA support were more engaged in wiki contributions. However, only the combination of cognitive and behavioral GA information, rather than their separate visualization, had a positive effect on resulting article quality. This highlights the need for a holistic perspective when developing GA tools to improve wiki processes and outcomes.

Behavior as a stereotype cue: An European Portuguese pretest on age and gender stereotypes

When it comes to the study of stereotypes, plenty of material can be of use. While personality traits tend to be the most commonly adopted, behavioral information can also be relevant, both in the study of stereotypes, as well as in other research fields (e.g., illusory correlations, memory and judgement and decision making). The purpose of this paper was to create a readily available list of behavioral sentences with stereotypicality ratings for both age (young to old) and gender (woman to man) categories, to be used in future studies. In two studies, participants judged age and gender stereotypicality of more than two hundred sentences in European Portuguese. Results were stable across both studies, using different methodologies (three alternative forced-choice task, in Study 1; bipolar rating scale, in Study 2). Relative frequencies for each choice, as well as average ratings, per behavior, are provided at the end.