Auxiliary Information-Enhanced Recommendations

Sequential recommendations have attracted increasing attention from both academia and industry in recent years. They predict a given user’s next choice of items by mainly modeling the sequential relations over a sequence of the user’s interactions with the items. However, most of the existing sequential recommendation algorithms mainly focus on the sequential dependencies between item IDs within sequences, while ignoring the rich and complex relations embedded in the auxiliary information, such as items’ image information and textual information. Such complex relations can help us better understand users’ preferences towards items, and thus benefit from the recommendations. To bridge this gap, we propose an auxiliary information-enhanced sequential recommendation algorithm called memory fusion network for recommendation (MFN4Rec) to incorporate both items’ image and textual information for sequential recommendations. Accordingly, item IDs, item image information and item textual information are regarded as three modalities. By comprehensively modelling the sequential relations within modalities and interaction relations across modalities, MFN4Rec can learn a more informative representation of users’ preferences for more accurate recommendations. Extensive experiments on two real-world datasets demonstrate the superiority of MFN4Rec over state-of-the-art sequential recommendation algorithms.

Formalizing Opponent Modeling with the Rock, Paper, Scissors Game

In simple dyadic games such as rock, paper, scissors (RPS), people exhibit peculiar sequential dependencies across repeated interactions with a stable opponent. These regularities seem to arise from a mutually adversarial process of trying to outwit their opponent. What underlies this process, and what are its limits? Here, we offer a novel framework for formally describing and quantifying human adversarial reasoning in the rock, paper, scissors game. We first show that this framework enables a precise characterization of the complexity of patterned behaviors that people exhibit themselves, and appear to exploit in others. This combination allows for a quantitative understanding of human opponent modeling abilities. We apply these tools to an experiment in which people played 300 rounds of RPS in stable dyads. We find that although people exhibit very complex move dependencies, they cannot exploit these dependencies in their opponents, indicating a fundamental limitation in people’s capacity for adversarial reasoning. Taken together, the results presented here show how the rock, paper, scissors game allows for precise formalization of human adaptive reasoning abilities.

Humans fail to outwit adaptive rock, paper, scissors opponents

How do humans adapt when others exploit patterns in their behavior? When can people modify such patterns and when are they simply trapped? The present work explores these questions using the children’s game of rock, paper, scissors (RPS). Adult participants played 300 rounds of RPS against one of eight bot opponents. The bots chose a move each round by exploiting unique sequential regularities in participant move choices. In order to avoid losing against their bot opponent, participants needed to recognize the ways in which their own behavior was predictable and disrupt the pattern. We find that for simple biases, participants were able to recognize that they were being exploited and even counter-exploit their opponents. However, for more complex sequential dependencies, participants were unable to change their behavior and lost reliably to the bots. Results provide a quantitative delineation of people’s ability to identify and alter patterns in their past decisions.

A general model of conversational dynamics and an example application in serious illness communication

Conversation has been a primary means for the exchange of information since ancient times. Understanding patterns of information flow in conversations is a critical step in assessing and improving communication quality. In this paper, we describe COnversational DYnamics Model (CODYM) analysis, a novel approach for studying patterns of information flow in conversations. CODYMs are Markov Models that capture sequential dependencies in the lengths of speaker turns. The proposed method is automated and scalable, and preserves the privacy of the conversational participants. The primary function of CODYM analysis is to quantify and visualize patterns of information flow, concisely summarized over sequential turns from one or more conversations. Our approach is general and complements existing methods, providing a new tool for use in the analysis of any type of conversation. As an important first application, we demonstrate the model on transcribed conversations between palliative care clinicians and seriously ill patients. These conversations are dynamic and complex, taking place amidst heavy emotions, and include difficult topics such as end-of-life preferences and patient values. We use CODYMs to identify normative patterns of information flow in serious illness conversations, show how these normative patterns change over the course of the conversations, and show how they differ in conversations where the patient does or doesn’t audibly express anger or fear. Potential applications of CODYMs range from assessment and training of effective healthcare communication to comparing conversational dynamics across languages, cultures, and contexts with the prospect of identifying universal similarities and unique “fingerprints” of information flow.

Not All Procedural Learning Tasks Are Difficult for Adults With Developmental Language Disorder

Purpose The experiment reported here compared two hypotheses for the poor statistical and artificial grammar learning often seen in children and adults with developmental language disorder (DLD; also known as specific language impairment). The procedural learning deficit hypothesis states that implicit learning of rule-based input is impaired, whereas the sequential pattern learning deficit hypothesis states that poor performance is only seen when learners must implicitly compute sequential dependencies. The current experiment tested learning of an artificial grammar that could be learned via feature activation, as observed in an associatively organized lexicon, without computing sequential dependencies and should therefore be learnable on the sequential pattern learning deficit hypothesis, but not on the procedural learning deficit hypothesis. Method Adults with DLD and adults with typical language development (TD) listened to consonant–vowel–consonant–vowel familiarization words from one of two artificial phonological grammars: Family Resemblance (two out of three features) and a control (exclusive OR, in which both consonants are voiced OR both consonants are voiceless) grammar in which no learning was predicted for either group. At test, all participants rated 32 test words as to whether or not they conformed to the pattern in the familiarization words. Results Adults with DLD and adults with TD showed equal and robust learning of the Family Resemblance grammar, accepting significantly more conforming than nonconforming test items. Both groups who were familiarized with the Family Resemblance grammar also outperformed those who were familiarized with the OR grammar, which, as predicted, was learned by neither group. Conclusion Although adults and children with DLD often underperform, compared to their peers with TD, on statistical and artificial grammar learning tasks, poor performance appears to be tied to the implicit computation of sequential dependencies, as predicted by the sequential pattern learning deficit hypothesis.

Sequential Dependencies in Solid and Fluid Intake in Nursing Home Residents with Dementia: A Multistate Model

Nursing home (NH) residents with dementia commonly experience low food intake leading to negative consequences. While multilevel factors influence intake, evidence is lacking on how intake is sequentially associated. This study examined the temporal association between previous and current solid and fluid intake in NH residents with dementia. We analyzed 160 mealtime videos involving 27 residents and 36 staff (53 dyads) in 9 NHs. The dependent variable was the current intake state (fluid, solid, no-intake). Independent variables included the prior intake state, technique of current intake state (resident-initiated, staff-facilitated), duration between previous and current intakes. Covariates included resident and staff characteristics. Two-way interactions of duration and technique with the prior intake state, and resident comorbidity and dementia severity were examined using Multinomial Logit Models. Interactions were significant for technique by comorbidity, technique by dementia severity, technique by prior fluid and solid intake, and duration by prior fluid intake. Successful previous intake increased odds of current solid and fluid intake. Staff-facilitation (vs. resident-initiation) reduced odds of solid and fluid intake for residents with moderately severe (vs. severe) dementia. Higher morbidity decreased odds of solid intake (vs. no-intake) for staff-facilitated intake. Resident with severe dementia had smaller odds of solid and fluid intake for resident-initiated intake. Longer duration increased odds of transition from liquid to solid intake. Findings supported strong sequential dependencies in intake, indicating the promise of intervening behaviorally to modify transitions to successful intake during mealtime. Findings inform the development and implementation of innovative mealtime assistance programs to promote intake.

Cognitive sequential dependencies in the wild: Sentiment analysis approach

Social networks data as naturally occurring data, are nowadays freely available toresearchers, and can constitute a unique source for exploring many theories in psychology andcognitive sciences. This paper investigates an effect known as cognitive sequential dependencein decision making, using five-point rating in term of review polarity index (RPI) of each user'sreviews by natural language processing about a services or businesses in YELP. In the presentstudy, the criteria for cognitive dependency in decisions is the degree of deviation of the presentRPI from the average of each user's RPIs. The statistical population consists of all user's reviewspublished by the YELP site, which contains over 6 million reviews. After some initialpreprocessing and filtering on textual reviews by Stanford CoreNLP tools in java, the linearregression analysis was performed on the reviews. Regression coefficients between deviationfrom mean of RPIs, with the RPI corresponded to different distances from current review up to 7distances against baseline, represented a statistically significant and strong relationships as wellas they revealed by going farther from current user decision, a subtle change from contrast effectto assimilation effect in users' decisions. While there are not usually a subtle matches betweenpolarity of explicit ratings (stars) and provided textual data in business websites , The promisingresults of this study suggest utilizing textual content of reviews as implicit ratings to trackcognitive sequential dependencies in the wild data and application of it for debasing algorithmand designing efficient online recommendation systems.

Learning Multi-Level Dependencies for Robust Word Recognition

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a robust word recognition framework that captures multi-level sequential dependencies in noised sentences. The proposed framework employs a sequence-to-sequence model over characters of each word, whose output is given to a word-level bi-directional recurrent neural network. We conduct extensive experiments to verify the effectiveness of the framework. The results show that the proposed framework outperforms state-of-the-art methods by a large margin and they also suggest that character-level dependencies can play an important role in word recognition. The code of the proposed framework and the major experiments are publicly available1.

Smart Computerized Essay Scoring Using Deep Neural Networks for Universities and Institutions

This chapter develops a web-based automated text scoring (ATS) system that can grade essays and check for spelling errors. The main reason behind this work is to alleviate the labour-intensive marking of essays and ensures equality in scoring for high-stakes exams like TOEFL. The researcher had performed a detailed investigation on deep learning techniques used in the field of ATS and developed a recurrent neural network model that can score essays in an end-to-end approach. Using the developed deep learning model, a web application was also developed to showcase the process of ATS by letting the web application to communicate with the trained model. The model was trained using Keras framework and TensorFlow library and the web application was done using the Flask framework. This work is the LSTM network that can capture sequential dependencies. The evaluation metrics chosen to evaluate the model are the quadratic weighted kappa (QWK) score, and the trained model can achieve 0.6 in QWK score.