The Effectiveness of Sentiment Analysis for Detecting Fine-grained Service Quality. GeoComputation 2019

Rahimi, Mohammad Masoud; Kakhki, Elham Naghi Zadeh; Winter, Stephan; Stevenson, Mark

doi:10.17608/k6.auckland.9848132.v2

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A preliminary version of this work has been presented before [45]. Compared to that paper, this work employs BERT, as a cutting-edge language model, to classify tweets into semantically-related aspects.…”

Section: Sentiment Analysis In Event Detectionmentioning

confidence: 99%

“…As shown in Figure 1, our proposed approach for the second task can be split into three steps, namely Frequency-based Event Detection, Sentiment-based Event detection, and statistic aggregation. Details on frequency-based event detection can be found in the initial version of this paper [45]. In this section, first we present the details of aspect-based sentiment analysis, and then the proposed approach for statistical aggregation of both methods.…”

Section: Detecting Events Of Interest Using Frequency and Sentiment A...mentioning

confidence: 99%

See 1 more Smart Citation

Service quality monitoring in confined spaces through mining Twitter data

Rahimi¹,

Naghizade²,

Stevenson³

et al. 2020

JOSIS

View full text Add to dashboard Cite

Promoting public transport depends on adapting effective tools for concurrent monitoring of perceived service quality. Social media feeds, in general, provide an opportunity to ubiquitously look for service quality events, but when applied to confined geographic area such as a transport node, the sparsity of concurrent social media data leads to two major challenges. Both the limited number of social media messages-leading to biased machine-learning-and the capturing of bursty events in the study period considerably reduce the effectiveness of general event detection methods. In contrast to previous work and to face these challenges, this paper presents a hybrid solution based on a novel finetuned BERT language model and aspect-based sentiment analysis. BERT enables extracting aspects from a limited context, where traditional methods such as topic modeling and word embedding fail. Moreover, leveraging aspect-based sentiment analysis improves the sensitivity of event detection. Finally, the efficacy of event detection is further improved by proposing a statistical approach to combine frequency-based and sentiment-based solutions. Experiments on a real-world case study demonstrate that the proposed solution improves the effectiveness of event detection compared to state-of-the-art approaches.

show abstract

Section: Sentiment Analysis In Event Detectionmentioning

confidence: 99%

Section: Detecting Events Of Interest Using Frequency and Sentiment A...mentioning

confidence: 99%