Abstract
As one of the hot research directions in natural language processing, sentiment analysis has received continuous and extensive attention. Different from explicit sentiment words indicating sentiment polarity, implicit sentiment analysis is a more challenging problem due to the lack of sentiment words, which makes it inadequate to use traditional sentiment analysis method to judge the polarity of implicit sentiment. This paper takes sentiment analysis as a special sign link prediction problem, which is different from traditional text-based method. In particular, by performing the word graph-based text level information embedding and heterogeneous social network information embedding (i.e. user social relationship network embedding, and user-entity sentiment network embedding), the proposed scheme learns the highly nonlinear representations of network nodes, explores early fusion method to combine the strength of these two types of embedding modeling, optimizes all parameters simultaneously and creates enhanced context representations, leading to better capture of implicit sentiment polarity. The proposed method has been examined on real-world dataset, for implicit sentiment link prediction task. The experimental results demonstrate that the proposed method outperforms state-of-the-art schemes, including LINE, node2vec, and SDNE, by 20.2%, 19.8%, and 14.0%, respectively, on accuracy, and achieves at least 14% gains on AUROC. For sentiment analysis accuracy, the proposed method achieves AUROC of 80.6% and accuracy of 78.3%, which is at least 31% better than other models. This work can provide useful guidance on the implicit sentiment analysis.
Highlights
The unstructured text generated by users, who share feelings and express attitudes in social media, contains users' behaviors in real life, and forms the sentiment links between these users and entities
To reveal the implicit sentiment polarity of social media short text, this paper explores and provides a novel angle to integrate user profiles and latent topics from text and social network structure, which is different from existing text-based methods
Our work is to study heterogeneous social network-based and text-based multiplex network embedding for implicit sentiment mining and analysis
Summary
The unstructured text generated by users, who share feelings and express attitudes in social media, contains users' behaviors in real life, and forms the sentiment links between these users and entities (e.g. commodities, movies or friends). In online social network platforms, the contents published by users are usually short sentences, clauses or phrases, and because people express their feelings or opinions in various ways, they can use explicit emotional words or implicit ones In this case, it is inadequate to use traditional sentiment classification algorithms to judge the polarity of sentiment relationship among uses and entities. Different context semantic backgrounds can result in different sentiment polarity In these situations, traditional sentiment analysis methods often fail to retrieve users’ hidden real attitudes, making it critical to be able to capture implicit sentiment, especially sentiment from the limited content published by users. Section “Experiment” carries out a variety of experiments and compared with some well-known network embedding methods and sentiment analysis algorithms
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.
