Music recommendation system based on user's sentiments extracted from social networks

Rosa, Renata Lopes; Rodríguez, Demóstenes Zegarra; Bressan, Graça

doi:10.1109/tce.2015.7298296

Cited by 82 publications

(26 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rapid growth of social media platforms such as microblogging services, social networking sites and short messaging services, people increasingly share their views and opinions online. As such, sentiment analysis has attracted much attention since opinions or sentiments detected from text are potentially useful for downstream applications including recommender systems [2], social network analysis [3], market forecasting [4] and the prediction of political topics [5].…”

Section: Introductionmentioning

confidence: 99%

Learning User and Product Distributed Representations Using a Sequence Model for Sentiment Analysis

Chen

et al. 2016

IEEE Comput. Intell. Mag.

105

View full text Add to dashboard Cite

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification in relation to reviews. However, existing approaches ignored the temporal nature of reviews posted by users or based on product evaluation. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pre-trained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated based on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-the-art results on these benchmark datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning User and Product Distributed Representations Using a Sequence Model for Sentiment Analysis

Chen

et al. 2016

IEEE Comput. Intell. Mag.

105

View full text Add to dashboard Cite

show abstract

“…Renata L. Rosa, Demóstenes Z. Rodríguez [4] This paper presents a music recommendation system based on a sentiment intensity metric, named enhanced Sentiment Metric(eSM) that is the association of a lexicon-based sentiment metric with a correction factor based on the user's profile. The solution does not include complex programming languages; consumes low resources from current electronic devices.…”

Section: Literature Surveymentioning

confidence: 99%

Recommendation System for Engineering Admission

2017

IJAERD

View full text Add to dashboard Cite

show abstract

“…In the study [4] they provided music according to the priorities of the users for the recommender system. The methodology of the recommender system has been provided according to the sentiments metric.…”

Section: Related Workmentioning

confidence: 99%

Improvement of recommender systems considering big data of users’ comments on chosen items

Esfandiari¹,

Honarvar²,

Aghamirzadeh³

2016

J. Fundam and Appl Sci.

View full text Add to dashboard Cite

Regarding to the increase in the online social networks services during the recent years, the recommender system has turned into an emerging research subject. Currently, regarding to the fast and consistent expansion of using the internet, the necessity of a recommender system for refining the large volume of data has increased greatly. The purpose of recommender systems is to provide a list of the interested items for the user and due to the increase in the current data volume, the previous used tools are nor suitable for processing this data volume; hence, having a system which can save and process the large data has turned into a problem. In this study, to solve the mentioned problems, a system is recommended using a model-based collaborative filtering refinement model which uses the Spark processing model in Hadoop context in order for more exact advising the user from the viewpoint of the users. The obtained results indicate that the current method will be more efficient and effective compared to the common recommendation methods.

show abstract

Music recommendation system based on user's sentiments extracted from social networks

Cited by 82 publications

References 28 publications

Learning User and Product Distributed Representations Using a Sequence Model for Sentiment Analysis

Learning User and Product Distributed Representations Using a Sequence Model for Sentiment Analysis

Recommendation System for Engineering Admission

Improvement of recommender systems considering big data of users’ comments on chosen items

Contact Info

Product

Resources

About