Abstract
Hyper-dense wireless network deployment is one of the popular solutions to meeting high capacity requirement for 5G delivery. However, current operator understanding of consumer satisfaction comes from call centers and base station quality-of-service (QoS) reports with poor geographic accuracy. The dramatic increase in geo-tagged social media posts adds a new potential to understand consumer satisfaction towards target-specific quality-of-experience (QoE) topics. In our paper, we focus on evaluating users’ opinion on wireless service-related topics by applying natural language processing (NLP) to geo-tagged Twitter data. Current generalized sentiment detection methods with generalized NLP corpora are not topic specific. Here, we develop a novel wireless service topic-specific sentiment framework, yielding higher targeting accuracy than generalized NLP frameworks. To do so, we first annotate a new sentiment corpus called SignalSentiWord (SSW) and compare its performance with two other popular corpus libraries, AFINN and SentiWordNet. We then apply three established machine learning methods, namely: Naive Bayes (NB), Support Vector Machine (SVM), and Recurrent Neural Network (RNN) to build our topic-specific sentiment classifier. Furthermore, we discuss the capability of SSW to filter noisy and high-frequency irrelevant words to improve the performance of machine learning algorithms. Finally, the real-world testing results show that our proposed SSW improves the performance of NLP significantly.
Highlights
SUMMARY AND FUTURE WORK In this paper, we have presented the structure, protocol and annotating process of our proposed SSW corpus for detecting consumer sentiment to wireless services
After comparing with two other popular corpus libraries, our results show that SSW has an advantage in both accuracy and expertise in ‘mobile signal blackspot’ sentiment classification
We have analyzed three popular machine learning methods when applied to our scenario and assessed the capability of combining the SSW corpus with ML methods
Summary
They suggested developing a new interface for LAN to parse users’ inquiry with NLP, which was designed for establishing the human-machine interaction These previous works have shown that, through properly pre-processing tweets (remove URL, tokenization, remove stop words and so on) and applying sentiment analysis on selected tweets, it is possible to summarize users’ opinions on specific topics at a high spatial resolution, which is wireless network in these works. Reference [17] introduced a novel approach for automatically classifying the sentiment of tweets with the help of NB and SVM These previous papers have been focusing on applying Machine learning methods to do sentiment analysis.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
