Interactive Sequential Basket Recommendation by Learning Basket Couplings and Positive/Negative Feedback

2021 ◽  
Vol 39 (3) ◽  
pp. 1-26
Author(s):  
Wei Wang ◽  
Longbing Cao
Keyword(s):  
Empirical Analysis ◽  
Negative Feedback ◽  
Positive Feedback ◽  
State Of The Art ◽  
Research Community ◽  
User Feedback ◽  
User Selection ◽  
Relevant Context ◽  
Interactive Recommendation ◽  
Interactive Feedback

Sequential recommendation , such as next-basket recommender systems (NBRS), which model users’ sequential behaviors and the relevant context/session, has recently attracted much attention from the research community. Existing session-based NBRS involve session representation and inter-basket relations but ignore their hybrid couplings with the intra-basket items, often producing irrelevant or similar items in the next basket. In addition, they do not predict next-baskets (more than one next basket recommended). Interactive recommendation further involves user feedback on the recommended basket. The existing work on next-item recommendation involves positive feedback on selected items but ignores negative feedback on unselected ones. Here, we introduce a new setting— interactive sequential basket recommendation , which iteratively predicts next baskets by learning the intra-/inter-basket couplings between items and both positive and negative user feedback on recommended baskets. A hierarchical attentive encoder-decoder model (HAEM) continuously recommends next baskets one after another during sequential interactions with users after analyzing the item relations both within a basket and between adjacent sequential baskets (i.e., intra-/inter-basket couplings) and incorporating the user selection and unselection (i.e., positive/negative) feedback on the recommended baskets to refine NBRS. HAEM comprises a basket encoder and a sequence decoder to model intra-/inter-basket couplings and a prediction decoder to sequentially predict next-baskets by interactive feedback-based refinement. Empirical analysis shows that HAEM significantly outperforms the state-of-the-art baselines for NBRS and session-based recommenders for accurate and novel recommendation. We also show the effect of continuously refining sequential basket recommendation by including unselection feedback during interactive recommendation.

scholarly journals Suppression of personality variation in boldness during foraging in three-spined sticklebacks

2021 ◽  
Vol 75 (4) ◽  
Author(s):  
Hannah E. A. MacGregor ◽  
Aislinn Cottage ◽  
Christos C. Ioannou
Keyword(s):  
Negative Feedback ◽  
Risk Taking ◽  
Positive Feedback ◽  
Gasterosteus Aculeatus ◽  
Control Treatment ◽  
Refuge Use ◽  
Individual Level ◽  
Behavioural Type ◽  
State Behaviour

Abstract Consistent inter-individual variation in behaviour within a population, widely referred to as personality variation, can be affected by environmental context. Feedbacks between an individual’s behaviour and state can strengthen (positive feedback) or weaken (negative feedback) individual differences when experiences such as predator encounters or winning contests are dependent on behavioural type. We examined the influence of foraging on individual-level consistency in refuge use (a measure of risk-taking, i.e. boldness) in three-spined sticklebacks, Gasterosteus aculeatus, and particularly whether changes in refuge use depended on boldness measured under control conditions. In the control treatment trials with no food, individuals were repeatable in refuge use across repeated trials, and this behavioural consistency did not differ between the start and end of these trials. In contrast, when food was available, individuals showed a higher degree of consistency in refuge use at the start of the trials versus controls but this consistency significantly reduced by the end of the trials. The effect of the opportunity to forage was dependent on behavioural type, with bolder fish varying more in their refuge use between the start and the end of the feeding trials than shyer fish, and boldness positively predicted the likelihood of feeding at the start but not at the end of the trials. This suggests a state-behaviour feedback, but there was no overall trend in how bolder individuals changed their behaviour. Our study shows that personality variation can be suppressed in foraging contexts and a potential but unpredictable role of feedbacks between state and behaviour. Significance statement In this experimental study, we examined how foraging influences consistency in risk-taking in individual three-spined sticklebacks. We show that bolder individuals become less consistent in their risk-taking behaviour than shyer individuals during foraging. Some bolder individuals reinforce their risk-taking behaviour, suggesting a positive feedback between state and behaviour, while others converge on the behaviour of shyer individuals, suggesting a negative feedback. In support of a role of satiation in driving negative feedback effects, we found that bolder individuals were more likely to feed at the start but not at the end of the trials. Overall, our findings suggest that foraging can influence personality variation in risk-taking behaviour; however, the role of feedbacks may be unpredictable.

scholarly journals Bayesian analysis of time-varying interactions between stock returns and foreign equity flows

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Boubekeur Baba ◽  
Güven Sevil
Keyword(s):  
Stock Returns ◽  
Negative Feedback ◽  
Positive Feedback ◽  
Positive Response ◽  
Time Varying ◽  
Economic Uncertainty ◽  
Foreign Investors ◽  
New Findings ◽  
Net Flows ◽  
Feedback Trading

AbstractThis study discusses the trading behavior of foreign investors with respect to economic uncertainty in the South Korean stock market from a time-varying perspective. We employ a news-based measure of economic uncertainty along with the model of time-varying parameter vector autoregression with stochastic volatility. The empirical analysis reveals several new findings about foreign investors’ trading behaviors. First, we find evidence that positive feedback trading often appears during periods of high economic uncertainty, whereas negative feedback trading is exclusively observable during periods of low economic uncertainty. Second, the foreign investors’ feedback trading appears mostly to be well-timed and often leads the time-varying economic uncertainty except in periods of global crises. Third, lagged negative (positive) response of net flows to economic uncertainty is found to be coupled with lagged positive (negative) feedback trading. Fourth, the study documents an asymmetric response of foreign investors with regard to negative and positive shocks of economic uncertainty. Specifically, we find that they instantly turn to positive feedback trading after a negative contemporaneous response of net flows to shocks of economic uncertainty. In contrast, they move slowly toward negative feedback trading after a positive response of net flows to uncertainty shocks.

scholarly journals Technology-enhanced and game based learning for children with special needs: a systematic mapping study

2021 ◽  
Author(s):  
Jose A. Gallud ◽  
Monica Carreño ◽  
Ricardo Tesoriero ◽  
Andrés Sandoval ◽  
María D. Lozano ◽  
...  
Keyword(s):  
Special Needs ◽  
State Of The Art ◽  
Research Community ◽  
Systematic Mapping Study ◽  
Children With Special Needs ◽  
Game Based Learning ◽  
Mapping Study ◽  
Systematic Mapping ◽  
Wide Range ◽  
Research Questions

AbstractTechnology-based education of children with special needs has become the focus of many research works in recent years. The wide range of different disabilities that are encompassed by the term “special needs”, together with the educational requirements of the children affected, represent an enormous multidisciplinary challenge for the research community. In this article, we present a systematic literature review of technology-enhanced and game-based learning systems and methods applied on children with special needs. The article analyzes the state-of-the-art of the research in this field by selecting a group of primary studies and answering a set of research questions. Although there are some previous systematic reviews, it is still not clear what the best tools, games or academic subjects (with technology-enhanced, game-based learning) are, out of those that have obtained good results with children with special needs. The 18 articles selected (carefully filtered out of 614 contributions) have been used to reveal the most frequent disabilities, the different technologies used in the prototypes, the number of learning subjects, and the kind of learning games used. The article also summarizes research opportunities identified in the primary studies.

scholarly journals A13-2 Identification of negative feedback, positive feedback and feed foward sequences during tilt test in young women with syncope

EP Europace ◽  
2003 ◽  
Vol 4 (Supplement_2) ◽  
pp. B19-B19
Author(s):  
G.A. Ruiz ◽  
J.C. Perfetto ◽  
S. Gallino ◽  
R. Chirife ◽  
A. Guillardot ◽  
...  
Keyword(s):  
Young Women ◽  
Negative Feedback ◽  
Positive Feedback ◽  
Tilt Test

EFFECT OF HYPOTHALAMIC DEAFFERENTATION ON THE CONTROL OF LUTEINIZING HORMONE SECRETION

1970 ◽  
Vol 46 (1) ◽  
pp. 1-7 ◽  
Author(s):  
S. TALEISNIK ◽  
M. E. VELASCO ◽  
J. J. ASTRADA
Keyword(s):  
Luteinizing Hormone ◽  
Negative Feedback ◽  
Positive Feedback ◽  
Hormone Secretion ◽  
Feedback Effect ◽  
Luteinizing Hormone Secretion ◽  
Ovarian Steroids ◽  
Medial Hypothalamus ◽  
Lh Release ◽  
Positive Feedback Effect

SUMMARY The influence that the interruption of the neural afferents to the hypothalamus exerts on ovulation and on the release of luteinizing hormone (LH) was studied in the rat. Animals with retrochiasmatic sections interrupting the neural connexions between the medial hypothalamus and the preoptic area (POA) showed constant oestrus and failed to ovulate. Animals in which the dorsal neural afferents to the POA were transected had oestrous cycles and ovulated normally. The positive feedback effect of progesterone on LH release in spayed animals primed either with 20 μg. oestradiol benzoate or 2·5 mg. testosterone propionate 3 days before was studied. Transection of the dorsal afferents to the POA favoured an increase in plasma LH, but in animals with retrochiasmatic sections the response was abolished. However, the negative feedback effect of ovarian steroids operated after both types of transection because an increase in plasma LH occurred after ovariectomy. It is concluded that the negative feedback effect of ovarian steroids acts on the medial hypothalamus which can maintain a tonic release of gonadotrophins in the absence of steroids. In contrast, the POA involved in the positive feedback effect of progesterone is concerned with the phasic release of LH.

FEEDBACK EFFECTS OF THYROXINE ON THE HYPOTHALAMUS AND PITUITARY OF GOLDFISH, CARASSIUS AURATUS

1971 ◽  
Vol 51 (1) ◽  
pp. 31-39 ◽  
Author(s):  
R. E. PETER
Keyword(s):  
Negative Feedback ◽  
Positive Feedback ◽  
Carassius Auratus ◽  
Feedback Effect ◽  
Inhibitory Factor ◽  
Pituitary Stalk ◽  
Thyroid Activity ◽  
Feedback Effects ◽  
Goldfish Carassius Auratus ◽  
Positive Feedback Effect

SUMMARY The effect on thyroid activity of a systemically ineffective dose of thyroxine (T4) implanted in the hypothalamus or pituitary of goldfish was tested. Thyroid activity was decreased by T4 implantation in either location, indicating that T4 has a negative feedback effect on the pituitary causing a decrease in thyrotrophin secretion, and a positive feedback effect on the hypothalamus stimulating the secretion of thyrotrophin inhibitory factor (TIF). Fish with a T4 or blank-control implant in the pituitary that had a damaged pituitary stalk, as a result of the operative procedures, were hyperthyroid, suggesting either that TIF is more effective in suppressing thyrotroph activity than T4 and that the effect of T4 was masked by the absence of TIF, or, less likely, that T4 negative feedback in the pituitary is not effective independent of TIF. The results were compared with the information about T4 feedback in mammals.

scholarly journals Solving Delete Free Planning with Relaxed Decision Diagram Based Heuristics

2020 ◽  
Vol 67 ◽  
pp. 607-651
Author(s):  
Margarita Paz Castro ◽  
Chiara Piacentini ◽  
Andre Augusto Cire ◽  
J. Christopher Beck
Keyword(s):  
Linear Programming ◽  
Empirical Analysis ◽  
State Of The Art ◽  
The State ◽  
Decision Diagrams ◽  
Binary Decision ◽  
Admissible Heuristics ◽  
The Cost ◽  
Construction Algorithms ◽  
Diagram Representation

We investigate the use of relaxed decision diagrams (DDs) for computing admissible heuristics for the cost-optimal delete-free planning (DFP) problem. Our main contributions are the introduction of two novel DD encodings for a DFP task: a multivalued decision diagram that includes the sequencing aspect of the problem and a binary decision diagram representation of its sequential relaxation. We present construction algorithms for each DD that leverage these different perspectives of the DFP task and provide theoretical and empirical analyses of the associated heuristics. We further show that relaxed DDs can be used beyond heuristic computation to extract delete-free plans, find action landmarks, and identify redundant actions. Our empirical analysis shows that while DD-based heuristics trail the state of the art, even small relaxed DDs are competitive with the linear programming heuristic for the DFP task, thus, revealing novel ways of designing admissible heuristics.

scholarly journals The Spiral of Positive Feedback: Go-Along Interviews About Adolescents’ Perceptions of and Reactions to Alcohol Posts on Social Media

2021 ◽  
pp. 002204262110414
Author(s):  
Robyn Vanherle ◽  
Kathleen Beullens ◽  
Hanneke Hendriks
Keyword(s):  
Social Media ◽  
Interpersonal Communication ◽  
Negative Feedback ◽  
Positive Feedback ◽  
Online Chat ◽  
Public And Private ◽  
Face To Face ◽  
Online Environments

Go-along interviews among adolescents ( N = 26, M age = 16.31, SD = .83) were conducted to examine how adolescents interpret alcohol posts in terms of appropriateness and how this, in turn, plays a role in adolescents’ reactions toward alcohol posts on public and private social media entries. The findings of this study, first, indicate that alcohol posts were classified as appropriate or inappropriate based on the amount of alcohol and the displayed behavior in the post. Second, most posts, including inappropriate ones, received positive or no feedback. Moreover, adolescents deliberately seemed to withhold negative feedback out of fear of being misjudged by peers. Still, negative reactions were expressed more quickly in safer off- and online environments (i.e., face-to-face conversation and online chat messages) because they were visible to close friends only. This is important in view of prevention as it unravels the interesting role of private environments in stimulating negative interpersonal communication.

scholarly journals Modeling Topical Relevance for Multi-Turn Dialogue Generation

2020 ◽  
Author(s):  
Hainan Zhang ◽  
Yanyan Lan ◽  
Liang Pang ◽  
Hongshen Chen ◽  
Zhuoye Ding ◽  
...  
Keyword(s):  
Topic Model ◽  
State Of The Art ◽  
Training Dataset ◽  
Common Phenomenon ◽  
New Model ◽  
Sentence Level ◽  
Topic Distribution ◽  
Topic Drift ◽  
Relevant Context ◽  
Customer Services

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations.

INTEGRATION OF POSITIVE AND NEGATIVE FEEDBACK LOOPS IN A CRAYFISH MUSCLE

1994 ◽  
Vol 187 (1) ◽  
pp. 305-313
Author(s):  
P Skorupski ◽  
P Vescovi ◽  
B Bush
Keyword(s):  
Negative Feedback ◽  
Positive Feedback ◽  
Motor Neurone ◽  
Chordotonal Organ ◽  
Negative Feedback Loops ◽  
Reflex Pathways ◽  
Motor Neurones ◽  
Receptor Organ ◽  
Group 2

It is now well established that in arthropods movement-related feedback may produce positive, as well as negative, feedback reflexes (Bassler, 1976; DiCaprio and Clarac, 1981; Skorupski and Sillar, 1986; Skorupski et al. 1992; Vedel, 1980; Zill, 1985). Usually the same motor neurones are involved in both negative feedback (resistance) reflex responses and positive feedback reflexes. Reflex reversal involves a shift in the pattern of central inputs to a motor neurone, for example from excitation to inhibition. In the crayfish, central modulation of reflexes has been described in some detail for two basal limb proprioceptors, the thoracocoxal muscle receptor organ (TCMRO) and the thoracocoxal chordotonal organ (TCCO) (Skorupski et al. 1992; Skorupski and Bush, 1992). Leg promotor motor neurones are excited by stretch of the TCMRO (which, in vivo, occurs on leg remotion) in a negative feedback reflex, but when this reflex reverses they are inhibited by the same stimulus. Release of the TCCO (which corresponds to leg promotion) excites some, but not all, promotor motor neurones in a positive feedback reflex. There are at least two ways in which the reflex control of a muscle may be modulated in this system. Firstly, inputs to motor neurones may be routed via alternative reflex pathways to produce different reflex outputs. Secondly, the pattern of inputs to a motor pool may be inhomogeneous, so that activation of different subgroups of the motor pool causes different outputs. Different crayfish promotor motor neurones are involved in different reflexes. On this basis, the motor neurones may be classified into at least two subgroups: those that are excited by the TCCO in a positive feedback reflex (group 1) and those that are not (group 2). Do these motor neurone subgroups have different effects on the promotor muscle, or is the output of the two promotor subgroups summed at the neuromuscular level? To address this question we recorded from the promotor nerve and muscle in a semi-intact preparation of the crayfish, Pacifastacus leniusculus. Adult male and female crayfish, 8-11 cm rostrum to tail, were decapitated and the tail, carapace and viscera removed. The sternal artery was cannulated and perfused with oxygenated crayfish saline, as described previously (Sillar and Skorupski, 1986).

Sign in / Sign up

Export Citation Format

Share Document