Artist Similarity Research Articles

Artist Similarity Based on Heterogeneous Graph Neural Networks

Artist Similarity Based on Heterogeneous Graph Neural Networks

Undecorated Tomb No. 18 at Beni Hassan and the Succession of Its Ruling Family


 
 
 The uninscribed and unfinished tomb No. 18 at Beni Hassan represents a key to understanding the architectural development of the tombs in this site as well as to the study of the succession of members of the nomarchic family of the 16th Upper Egyptian province. The location, approach, and design of the chapel, as well as the number and type of architraves and columns place the tomb immediately after the neighbouring one, No. 17, of Khety I, and make it likely that it belonged to the latter’s son, Khety II. It is argued that following the successive deaths of Khety I and Khety II, probably due to the bellicose conditions at the time, Khnumhotep I of tomb No. 14, a likely son or descendant of Baqet III of tomb No. 15, became a governor and cut his tomb adjacent to that of the latter. The architectural and artistic similarities between the two tombs are striking. An examination of the skeletal remains of Baqet II, Khety I, and probably Khety II, shows evidence of a possible involvement in wars and indicates that they died at young age. The representation of specific individuals and certain themes in a number of tombs at Beni Hassan suggests that these tombs belonged to members of the same family and that all date to a relatively short period in the second half of the Eleventh Dynasty and the first half of the Twelfth.
 
 

Artist Similarity for Everyone: A Graph Neural Network Approach

Artist similarity plays an important role in organizing, understanding, and subsequently, facilitating discovery in large collections of music. In this paper, we present a hybrid approach to computing similarity between artists using graph neural networks trained with triplet loss. The novelty of using a graph neural network architecture is to combine the topology of a graph of artist connections with content features to embed artists into a vector space that encodes similarity. Additionally, we propose a simple and effective regularization method—<em>connection dropout</em>—which aims at improving results for long-tail artists, for which few existing connections are known. To evaluate the proposed method, we use two datasets: the open OLGA dataset, which contains artist similarities from AllMusic, together with content features from AcousticBrainz, and a larger, proprietary dataset. We find that using graph neural networks yields superior overall results compared to state-of-the-art methods. Beyond the overall evaluation, we investigate the effectiveness of the proposed model for long-tail artists. Such artists may benefit less from graph-based methods, since they typically have few known connections. We show that the proposed regularization approach clearly improves the performance for long-tail artists, without negatively affecting results for well-connected ones; it computes high-quality embeddings and good similarity scores for everyone.

Music genre influence and artist similarity based on data analysis

Based on related data and cluster analysis, this paper creates a mathematical model of similarity measurement based on the data set, and finally obtains the influence of different music genres on their followers and the similarity of artists of different musical genres. Here, since the study is about the similarity of music, it is divided into 2 categories according to the provided music characteristics and related indicators of music type. The data is standardized and normalized. Because there is no clear indicator to measure the similarity of music, we use spss to perform K-means clustering analysis. Here, since the similarity of music is studied, it is built on the music characteristics and music provided. Types of related indicators divide it into two categories for analysis. In order to determine the reliability of the model, this article uses meaningful learning to train 70% of the previous data, 30% to test, and finally establishes a complete mathematical model.

Research on Music Influence Evaluation System Based on Similarity Measure and Grey Relational Analysis

Music is an important part of the spiritual home of human beings, and it influences every generation with its own unique advantages. This paper explored the influence of music through the establishment of a directed network of music influence and a similarity measurement model, studied the evolution of music, and analyzed the influence process of the evolution. The research in this article explained the influence of music, the influence relationship between musicians and the evolution of music, which could make music develop better. We needed to solve the problems of artist similarity, genre similarity, and musical feature appeal. In this regard, we built a similarity evaluation model, read the music data set, and selected data for the indicators. We used principal component analysis to reduce the dimensionality of the index data, and then calculated the similarity based on Euclidean distance. For artist similarity, we divided it into the same genre and different genres, and we calculated that artists of the same genre were more similar than artists of different genres. For genre similarity, we calculated and drew a heat map of genre similarity. For the appeal of music features, we calculated the correlation between each feature and the popularity index based on the gray correlation analysis, and concluded that valence is the most infectious. This paper made full use of the music data obtained, described and quantified the influence of music from multiple aspects. The model in this paper is reasonable and realistic. The model can also be used to measure the impact of other occupations in society, and has a certain generalization.

EDIFICIO 4, TULA GRANDE: ARCHITECTURE, OCCUPATION, AND ABANDONMENT

AbstractThis article summarizes recent excavations of Edificio 4 in the Early Postclassic city of Tula, Hidalgo, which, despite prior evidence of its considerable importance, was largely unexcavated. Despite changes in strategy that resulted in discontinuous rather than complete exposure, excavation successfully delineated the entire structure and exposed portions of all or virtually all of its interior rooms, revealing a layout and architectural features notably different from those of the other buildings in Tula's monumental center, and suggest that Edificio 4 had functioned as a palace whose occupants were closely tied to Pyramid B, one of Tula's two largest pyramids. These excavations provide additional perspectives on previously noted similarities between Edificio 4 and the Casa de las Águilas of Aztec Tenochtitlan, revealing striking similarities in layout which, together with equally striking artistic similarities noted previously, make it almost certain that a major portion of the Casa de las Águilas was constructed in the image of the corresponding portion of Tula's Edificio 4.

THE PROBLEM OF A POSITIVE HERO IN H. BÖLL’S NOVEL “BILLIARDS AT HALF PAST NINE” IN THE CONTEXT OF THE LITERARY INFLUENCE OF F.M. DOSTOEVSKY

The paper examines the peculiarities of the reception of the artistic experience of F.M. Dostoevsky by the German writer H. Böll at the level of the figurative system of the novel “Billiards at half-past nine”. A comprehensive comparative analysis of the images of Makar Dolgoruky and Shrella allows us to reveal a number of artistic similarities between these characters, manifested both in terms of character disclosure (the presence in both characters such qualities as humility, insight, moral hardness, religiosity) as well as in the aspect of artistic functions (the role they play as a moral guide for central characters). This confirms the fact that in this work there are signs of the literary influence of F.M. Dostoevsky on the creative style of H. Böll. At the same time, the problem of a positive hero in the novel “Billiards at half-past nine” is developed on the material of the German post-war reality in close connection with the historical and political context. The German writer creates an original image of a distinctive character, imbued with special symbolism.

Recognizing Musical Entities in User-generated Content

Recognizing Musical Entities is important for Music Information Retrieval (MIR) since it canimprove the performance of several tasks such as music recommendation, genre classification or artist similarity. However, most entity recognition systems in the music domain have concentrated on formal texts (e.g. artists’ biographies, encyclopedic articles, etc.), ignoring rich and noisy user-generated content. In this work, we present a novel method to recognize musicalentities in Twitter content generated by users following a classical music radio channel. Our approach takes advantage of both formal radio schedule and users’ tweets to improve entity recognition. We instantiate several machine learning algorithms to perform entity recognition combining task-specific and corpus-based features. We also show how to improve recognition results by jointly considering formal and user-generated content.

Fashion and art cycles are driven by counter-dominance signals of elite competition: quantitative evidence from music styles.

Human symbol systems such as art and fashion styles emerge from complex social processes that govern the continuous re-organization of modern societies. They provide a signalling scheme that allows members of an elite to distinguish themselves from the rest of society. Efforts to understand the dynamics of art and fashion cycles have been placed on 'bottom-up' and 'top-down' theories. According to 'top-down' theories, elite members signal their superior status by introducing new symbols (e.g. fashion styles), which are adopted by low-status groups. In response to this adoption, elite members would need to introduce new symbols to signal their status. According to many 'bottom-up' theories, style cycles evolve from lower classes and follow an essentially random pattern. We propose an alternative explanation based on counter-dominance signalling (CDS). In CDS, elite members want others to imitate their symbols; changes only occur when outsider groups successfully challenge the elite by introducing signals that contrast those endorsed by the elite. We investigate these mechanisms using a dynamic network approach on data containing almost 8 million music albums released between 1956 and 2015. The network systematically quantifies artistic similarities of competing musical styles and their changes over time. We formulate empirical tests for whether new symbols are introduced by current elite members (top-down), randomness (bottom-up) or by peripheral groups through counter-dominance signals. We find clear evidence that CDS drives changes in musical styles. This provides a quantitative, completely data-driven answer to a century-old debate about the nature of the underlying social dynamics of fashion cycles.

Music Clustering With Features From Different Information Sources

Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying ldquosimilarrdquo artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.

The Chronocultural Sequence of Belgian Complexes in the European Aurignacian Context

The study of Aurignacian collections from the Meuse Basin, associated with recent fieldwork data, has led to a new overview of the Aurignacian in this region. This work discredits some of the hypotheses advanced for the earliest Aurignacian occupations in north-western Europe and proposes a hypothetical chronocultural sequence based on the most reliable data for this period. The Meuse Basin presents an important concentration of Aurignacian occupations, some of them very rich and this zone is therefore conducive to large scale comparisons, in particular with regions with a better defined chronostratigraphic framework. The existence of technical and artistic similarities between these different European regions also highlights the strong links binding the Aurignacian complex, and is probably an important element for understanding the transition from the Middle Paleolithic to the Upper Paleolithic in Europe.

Using Species Distribution Modeling to contextualize Lower Magdalenian social networks visible through portable art stylistic similarities in the Cantabrian region (Spain)

This research argues for a refocus of the study of prehistoric social networks that involves contextualizing the inter-site links that are often interpreted as indicators of inter-site social interactions. It focuses on the social networks created during the Lower Magdalenian of the Cantabrian region (Spain), and visible through similarities of portable art representations. It uses Species Distribution Modeling and Maximum Classification Likelihood on faunal presence data to reconstruct prehistoric biomes, and contextualize the networks reconstructed through the art analysis. It demonstrates the potential of mapping the recreated networks onto the reconstructed biomes and of identifying the linked sites' foraging and minimal band territories to distinguish between local mobility movement and inter-group social alliances. The results show that, during the Lower Magdalenian, the majority of movements seen through artistic similarities probably represent the seasonal mobility of one or two hunter-gatherer groups, and that only a few inter-site links represent social networks used to exchange mates and gather information.

Harvesting microblogs for contextual music similarity estimation: a co-occurrence-based framework

Microtexts are a valuable, albeit noisy, source to infer collaborative information. As music plays an important role in many human lives, microblogs on music-related activities are available in abundance. This paper investigates different strategies to estimate music similarity from these data sources. In particular, we first present a framework to extract co-occurrence scores between music artists from microblogs and then investigate 12 similarity estimation functions to subsequently derive resemblance scores. We evaluate the approaches on a collection of microblogs crawled from Twitter over a period of 10 months and compare them to standard tf-idf approaches. As evaluation criteria we use precision and recall in an artist retrieval task as well as rank proximity. We show that collaborative chatter on music can be effectively used to develop music artist similarity measures, which are a core part of every music retrieval and recommendation system. Furthermore, we analyze the effects of the “long tail” on retrieval results and investigate whether results are consistent over time, using a second dataset.

Hierarchical Co-Clustering: A New Way to Organize the Music Data

In music information retrieval (MIR) an important research topic, which has attracted much attention recently, is the utilization of user-assigned tags, artist-related style, and mood labels, which can be extracted from music listening web sites, such as Last.fm (http://www.last.fm/) and All Music Guide (http://www.allmusic.com/). A fundamental research problem in the area is how to understand the relationships among artists/songs and these different pieces of information. Co-clustering is the problem of simultaneously clustering two types of data (e.g., documents and words, and webpages and urls). We can naturally bring this idea to the situation at hand and consider clustering artists and tags together, artists and styles together, or artists and mood labels together. Once such co-clustering has been successfully completed, one can identify co-existing clusters of artists and tags, styles, or mood labels (T/S/M). For simplicity, we use the acronym T/S/M to refer to tag(s), style(s), or mood(s) for the rest of the paper. When dealing with tags it is worth noticing that some tags are more specific versions of others. This naturally suggests that the tags could be organized in hierarchical clusters. Such hierarchical organizations exist for styles and mood labels, so we will consider hierarchical co-clustering of artists and T/S/M. In this paper, we systematically study the application of hierarchical co-clustering (HCC) methods for organizing the music data. There are two standard strategies for hierarchical clustering. One is the divisive strategy, in which we attempt to divide the input data set into smaller groups recursively, and the other is the agglomerative strategy, in which we attempt to combine initially individually separated data points into larger groups by finding the most closely related pair at each iteration. We will compare these two strategies against each other. We apply a previously known divisive hierarchical co-clustering method and a novel agglomerative hierarchical co-clustering. In addition, we demonstrate that these two methods have the capability of incorporating instance-level constraints to achieve better performance. We perform experiments to show that these two hierarchical co-clustering methods can be effectively deployed for organizing the music data and they present reasonable clustering performance comparing with the other clustering methods. A case study is also conducted to show that HCC provides us a new method to quantify the artist similarity.

Isolation concepts for clique enumeration: Comparison and computational experiments

We do computational studies concerning the enumeration of isolated cliques in graphs. Isolation, as recently introduced, measures the degree of connectedness of the cliques to the rest of the graph. Isolation helps both in getting faster algorithms for the enumeration of maximal general cliques and in filtering out cliques with special semantics. We compare three isolation concepts and their combination with two enumeration modi for maximal cliques (“isolated maximal” vs “maximal isolated”). All studied concepts exhibit the fixed-parameter tractability of the enumeration task with respect to the parameter “degree of isolation”. We provide a first systematic experimental study of the corresponding enumeration algorithms, using synthetic graphs (in the G n , m , p model), financial networks, and a music artist similarity network, proposing the enumeration of isolated cliques as a useful instrument in analyzing financial and social networks.

Music Clustering With Features From Different Information Sources

Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying ldquosimilarrdquo artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.

Did Meyerhold Influence Brecht? A Comparison of Their Antirealistic Theatrical Aesthetics

As two of the most important twentieth-century theatre directors, Bertolt Brecht and Vsevolod Meyerhold shared striking artistic, personal, and professional similarities. In addition to their middle-class background, both were the sons of merchants, well educated, politically persecuted, and exposed to the cultural innovations that spread throughout Germany and Russia during the 1920s and 1930s. Although Brecht's legacy is more salient, Meyerhold's artistic contributions can be traced to the work of numerous successors, including Brecht himself.

Else Lasker‐Schüler and Franz Marc

This essay investigates the relationship and artistic similarities between the poetess Else Lasker‐Schüler and the painter Franz Marc with regard to their friendship, their similar background and development, their artistic goals, and the actual development of their style. Both abhorred the modern technological world, for example, and sought in their works to create an innocent, child‐like atmosphere, to revitalize the natural and primordial drives, and to create a new mythological tone. In their style they both progressed from a rather uncontrolled, fanciful structure, very similar in ambience to Jugendstil, to a carefully conceived and highly compressed form of creativity which was based in a mosaic‐like constellation of motifs and images. The close relationship between poetess and painter can be viewed as typical of the interworkings of literature and art of the Expressionist period.