Music Mood Dataset Creation Based on Last FM Tags

Çano, Erion; Morisio, Maurizio

doi:10.5121/csit.2017.70603

Cited by 22 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the effectiveness of privacy preservation and the accuracy of the recommendation results on a multi-task knowledge graph enhanced recommendation system. The experiments are conducted on three commonly recommendation system datasets: MovieLens-1M [36], Book-Crossing [37] and Last.FM [38]. The experimental results show that our multi-task recommendation system with differential privacy guarantee is feasible without significant impact on the prediction accuracy of recommendation.…”

Section: Methodsmentioning

confidence: 90%

A Privacy-Preserving Multi-Task Framework for Knowledge Graph Enhanced Recommendation

Zhou

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Multi-task learning (MTL) is a learning paradigm which can improve generalization performance by transferring knowledge among multiple tasks. Traditional collaborative filtering recommendation methods suffer from cold start, sparsity and scalability problems. The latest research has shown that applying side information of knowledge graph can not only solve the problems above, but also improve the accuracy of recommendation. However, existing multi-task methods for knowledge graph enhanced recommendation expose obvious issues of disclosing the private information of training samples. In order to solve these problems, we put forward a privacy-preserving multi-task framework for knowledge graph enhanced recommendation. In specific, Laplacian noise is added into the recommendation module to guarantee the privacy of sensitive data and knowledge graph is utilized to improve the accuracy of recommendation. Extensive experimental results on three datasets demonstrate that the proposed method can not only preserve the privacy of sensitive training data, but also have little effect on the prediction accuracy of the model.

show abstract

Section: Methodsmentioning

confidence: 90%

A Privacy-Preserving Multi-Task Framework for Knowledge Graph Enhanced Recommendation

Zhou

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Despite this, Last.fm has been broadly used [19,22] in music sentiment analysis tasks, even though obtained datasets are not made public. Indeed, as already underlined in [11], as far as may be difficult to believe, still today no lyrics sentiment dataset fulfills all the four conditions mentioned before. In this context, the Italian music scenario is even more dramatic.…”

Section: Introductionmentioning

confidence: 91%

“…In the last decade, particular attention turned on corpus-based methods. Despite creating songs polarity tagged datasets is not an easy task [11], datasets of songs labeled with emotions, and polarity tagged lexicons are essentials prerequisite to computer those classification models. As suggested in [11], a music dataset should observe four main characteristics, such as (a) strong polarization; (b) easily understandable labels taxonomy; (c) high coverage and large size (at least 1,000 lyrics); and (d) publicly available.…”

Section: Introductionmentioning

confidence: 99%

The italian music superdiversity

Pollacci

Guidotti

Rossetti

et al. 2018

Multimed Tools Appl

View full text Add to dashboard Cite

Globalization can lead to a growing standardization of musical contents. Using a cross-service multi-level dataset we investigate the actual Italian music scene. The investigation highlights the musical Italian superdiversity both individually analyzing the geographical and lexical dimensions and combining them. Using different kinds of features over the geographical dimension leads to two similar, comparable and coherent results, confirming the strong and essential correlation between melodies and lyrics. The profiles identified are markedly distinct one from another with respect to sentiment, lexicon, and melodic features. Through a novel application of a sentiment spreading algorithm and songs' melodic features, we are able to highlight discriminant characteristics that violate the standard regional political boundaries, reconfiguring them following the actual musical communicative practices.

show abstract

“…The task here is to automatically predict the emotional category of each song text. To comply with the other tasks (binary classification) we use MLPN, a similar dataset of 2,500 positive and 2,500 negative song lyrics constructed from Last.fm user tags and a systematic process described in [19]. Both datasets can be freely downloaded from http://softeng.polito.it/erion/.…”

Section: Datasetsmentioning

confidence: 99%

A deep learning architecture for sentiment analysis

Çano

Morisio

2018

Proceedings of the International Conference on Geoinformatics and Data Analysis

Self Cite

View full text Add to dashboard Cite

The fabulous results of Deep Convolution Neural Networks in computer vision and image analysis have recently attracted considerable attention from researchers of other application domains as well. In this paper we present NgramCNN, a neural network architecture we designed for sentiment analysis of long text documents. It uses pretrained word embeddings for dense feature representation and a very simple single-layer classifier. The complexity is encapsulated in feature extraction and selection parts that benefit from the effectiveness of convolution and pooling layers. For evaluation we utilized different kinds of emotional text datasets and achieved an accuracy of 91.2 % accuracy on the popular IMDB movie reviews. NgramCNN is more accurate than similar shallow convolution networks or deeper recurrent networks that were used as baselines. In the future, we intent to generalize the architecture for state of the art results in sentiment analysis of variable-length texts. CCS Concepts • Computing methodologies ➝ Artificial intelligence ➝ Natural language processing • Applied Computing ➝ Document management and text processing

show abstract

Music Mood Dataset Creation Based on Last FM Tags

Abstract: ABSTRACT

Cited by 22 publications

References 19 publications

A Privacy-Preserving Multi-Task Framework for Knowledge Graph Enhanced Recommendation

A Privacy-Preserving Multi-Task Framework for Knowledge Graph Enhanced Recommendation

The italian music superdiversity

A deep learning architecture for sentiment analysis

Contact Info

Product

Resources

About