Abstract
This study presents a novel research approach to predict user interaction for social media post using machine learning algorithms. The posts are converted to vector form using word2vec and doc2vec model. These two methods are used to analyse the best approach for generating word embeddings. The generated word embeddings of post combined with other attributes like post published time, type of post and total interactions are used to train machine learning algorithms. Deep neural network (DNN), Extreme Learning Machine (ELM) and Long Short-Term Memory (LSTM) are used to compare the prediction of total interaction for a particular post. For word2vec, the word vectors are created using both continuous bag-of-words (CBOW) and skip-gram models. Also the pre-trained word vectors provided by google is used for the analysis. For doc2vec, the word embeddings are created using both the Distributed Memory model of Paragraph Vectors (PV-DM) and Distributed Bag of Words model of Paragraph Vectors (PV-DBOW). A word embedding is also created using PV-DBOW combined with skip-gram.
Highlights
Social media has become an important part of people’s lives
As mentioned in [24], continuous bag-of-words (CBOW) architecture works better on syntactic tasks and our problem is a syntactic problem where each post words combined together has a certain meaning and its vector representation combined with other 5 inputs performed well in predicting total interactions. This analysis is validated by google w2v which was trained on CBOW architecture
It is observed that peak value of R2 for all models in Long Short-Term Memory (LSTM) except CBOW performed better than their outcomes in Artificial Neural Network (ANN) because in LSTM along with current input, previous input information is preserved to predict total interaction
Summary
Social media has become an important part of people’s lives. It helps in creating content and sharing information among virtual communities and networks. Users spend a lot of time on social networking sites (SNS) like Facebook, LinkedIn and Twitter to interact with each other. Organizations have understood the potential of social media and are exploiting it to promote their products and analyze customer satisfaction [1]. Researchers are trying to understand human behavior on these platforms by adopting different strategies like viral product design [2], information diffusion model [3], network diffusion [4] and user influence [5]– [7]. As of September 2017, Facebook stands first for the number of active users on any SNS [8] with 2,072 million monthly active users (MAUs) [9] and is still growing
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
