Deep Learning-Based Context-Aware Recommender System Considering Contextual Features

A context-aware recommender system can make recommendations to users by considering contextual information such as time and place, not only the scores assigned to items by users. However, as a user preferences matrix is expanded in a multidimensional matrix, data sparsity is maximized. In this paper, we propose a deep learning-based context-aware recommender system that considers the contextual features. Based on existing deep learning models, we combine a neural network and autoencoder to extract characteristics and predict scores in the process of restoring input data. The newly proposed model is able to easily reflect various type of contextual information and predicts user preferences by considering the feature of user, item and context. The experimental results confirm that the proposed method is mostly superior to the existing method in all datasets. Also, for the dataset with data sparsity problem, it was confirmed that the performance of the proposed method is higher than that of existing methods. The proposed method has higher precision by 0.01–0.05 than other recommender systems in a dataset with many context dimensions. And it showed good performance with a high precision of 0.03 to 0.09 in a small dimensional dataset.

Revisited interpretation of Ta’ārof

Speech acts used in doing ta’ārof (Iranian system of politeness) have been conceptualized in terms of both positive (i.e. sincere or genuine) and negative (i.e. ritual or ostensible) meanings. This study aimed to revisit the interpretation of the negative meaning by concentrating on ta’ārof (ritual) offers produced by characters in Iranian films. First, these items were identified and distinguished from their genuine counterparts based on the strategies used in their structures and analysing their contextual features respectively. Then, the researcher proposed a model in which she adopted the notion of Leech’s (1983) meta-implicature (indirect implicature) to explicate the negative meaning of ta’ārof offers. She grouped a series of effective factors in working out these meta-implicatures. Finally, a tentative hierarchy of stages for identification and interpretation of ta’ārof offers in Iranian films were proposed.

Birds of a feather don’t fact-check each other: Partisanship and the evaluation of news in Twitter’s Birdwatch crowdsourced fact-checking program

There is a great deal of interest in the role that partisanship, and cross-party animosity in particular, plays in interactions on social media. Most prior research, however, must infer users’ judgments of others’ posts from engagement data. Here, we leverage data from Birdwatch, Twitter’s crowdsourced fact-checking pilot program, to directly measure judgments of whether other users’ tweets are misleading, and whether other users’ free-text evaluations of third-party tweets are helpful. For both sets of judgments, we find that contextual features – in particular, the partisanship of the users – are far more predictive of judgments than content features. Specifically, users are more likely to write negative evaluations of tweets from counter-partisans; and are more likely to rate evaluations from counter-partisans as unhelpful. Our findings provide clear evidence that users systematically reject content from those with whom they disagree politically. Platform designers must consider the ramifications of partisanship when implementing crowdsourcing programs.

Onset and Contiguity

Onset (metric position) and contiguity (pitch adjacency and time proximity) are two melodic features that contribute to the salience of individual notes (core tones) in a monophonic voice or polyphonic texture. Our approach to reductions prioritizes contextual features like onset and contiguity. By awarding points to notes with such features, our process selects core tones from melodic surfaces to produce a reduction. Through this reduction, a new form of musical pattern discovery is possible that has similarities to Gjerdingen’s (".fn_cite_year($gjerdingen_2007).") galant schemata. Recurring n-grams (scale degree skeletons) are matched in an algorithmic approach that we have tested manually (with a printed score and pen and paper) and implemented computationally (with symbolic data and scripted algorithms in MATLAB). A relatively simple method successfully identifies the location of all statements of the subject in Bach’s Fugue in C Minor (BWV 847) identified by Bruhn (".fn_cite_year($bruhn_1993).") and the location of all instances of the Prinner and Meyer schemata in Mozart’s Sonata in C Major (K. 545/i) identified by Gjerdingen (".fn_cite_year($gjerdingen_2007)."). We also apply the method to an excerpt by Kirnberger analyzed in Rabinovitch (".fn_cite_year($rabinovitch_2019)."). Analysts may use this flexible method for pattern discovery in reduced textures through software freely accessible at https://www.atavizm.org. While our case studies in the present article are from eighteenth-century European music, we believe our approach to reduction and pattern discovery is extensible to a variety of musics.

The effect of gender agreement mismatches on intersentential anaphoric pronouns

This article focuses on the effect of gender agreement mismatches between personal pronouns and their antecedents across sentences. In two acceptability experiments, we test whether acceptability of gender agreement violations on animated nouns may be modulated by grammatical and contextual features of the antecedents of personal pronouns. In the first experiment, we manipulated the “specificity” feature of the antecedent in order to make the antecedent refer either to the class of individuals or to a specific referent. In the second experiment, we used stereotypically male or female proper names to test whether grammatical gender mismatches between personal pronouns and bigender nouns could be attenuated. Although the first experiment showed an effect explainable purely by grammatical factors, against many theories of “semantic” agreement, the results of the second experiment suggest that both the grammatical and the contextual features of the antecedent are computed when speakers evaluate agreement relations between personal pronouns and their antecedents.

Exploring register with The Prime Machine

Corpus approaches underpin a range of postgraduate studies and professional work in language, linguistics, translation and beyond. Awareness of the influences of contextual features on language choice is important for many activities: exploring new text varieties; finding relationships between social factors and language patterning; considering choices for post-editing machine translation; and understanding the very nature of language. Work on register relies on corpus methods, but more support and direction could be offered to help undergraduates gain earlier insights into the power of such corpus analysis. This paper introduces some ways register differences can be revealed through The Prime Machine corpus tool (Jeaco 2017a) and describes the design of a practically-oriented undergraduate module which uses this concordancer. Software features include the organization of texts and presentation of source information for readymade corpora, and methods which can be used to reveal useful starting points for register analysis of do-it-yourself corpora.

Evaluating the Ability to Use Contextual Features Derived from Multi-Scale Satellite Imagery to Map Spatial Patterns of Urban Attributes and Population Distributions

With an increasing global population, accurate and timely population counts are essential for urban planning and disaster management. Previous research using contextual features, using mainly very-high-spatial-resolution imagery (<2 m spatial resolution) at subnational to city scales, has found strong correlations with population and poverty. Contextual features can be defined as the statistical quantification of edge patterns, pixel groups, gaps, textures, and the raw spectral signatures calculated over groups of pixels or neighborhoods. While they correlated with population and poverty, which components of the human-modified landscape were captured by the contextual features have not been investigated. Additionally, previous research has focused on more costly, less frequently acquired very-high-spatial-resolution imagery. Therefore, contextual features from both very-high-spatial-resolution imagery and lower-spatial-resolution Sentinel-2 (10 m pixels) imagery in Sri Lanka, Belize, and Accra, Ghana were calculated, and those outputs were correlated with OpenStreetMap building and road metrics. These relationships were compared to determine what components of the human-modified landscape the features capture, and how spatial resolution and location impact the predictive power of these relationships. The results suggest that contextual features can map urban attributes well, with out-of-sample R2 values up to 93%. Moreover, the degradation of spatial resolution did not significantly reduce the results, and for some urban attributes, the results actually improved. Based on these results, the ability of the lower resolution Sentinel-2 data to predict the population density of the smallest census units available was then assessed. The findings indicate that Sentinel-2 contextual features explained up to 84% of the out-of-sample variation for population density.

Contextual features for implementing epistemic modality in a common sense and in terms of gender

The subject of this research is epistemic modality, which is referred to a subjective type of modality in a common sense and in terms of gender; it is considered as the connection between a subject and an attribute. The purpose of this research is to study epistemic modality and its contextual features in a common sense and in terms of gender. The objectives of this article require application of several methods such as comparative analysis and text analysis. The methods favour the fact that the conclusions concerning the means of epistemic modality expression are maximally reliable. The method of continuous sampling was used to accumulate actual materials in terms of the gender approach. In the course of this study, the different types of epistemic modality such as epistemic modality of certainty / uncertainty, epistemic modality expressing the meaning of opinion – assumption, doubtful evaluation.