Semi-Supervised Iterative Approach for Domain-Specific Complaint Detection in Social Media
In this paper, we present a semi-supervised bootstrapping approach to detect product or service related complaints in social media. Our approach begins with a small collection of annotated samples which are used to identify a preliminary set of linguistic indicators pertinent to complaints. These indicators are then used to expand the dataset. The expanded dataset is again used to extract more indicators. This process is applied for several iterations until we can no longer find any new indicators. We evaluated this approach on a Twitter corpus specifically to detect complaints about transportation services. We started with an annotated set of 326 samples of transportation complaints, and after four iterations of the approach, we collected 2,840 indicators and over 3,700 tweets. We annotated a random sample of 700 tweets from the final dataset and observed that nearly half the samples were actual transportation complaints. Lastly, we also studied how different features based on semantics, orthographic properties, and sentiment contribute towards the prediction of complaints.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
An Iterative Approach for Identifying Complaint Based Tweets in Social Media Platforms
Twitter is a social media platform where users express opinions over a variety of issues. Posts offering grievances or complaints can be utilized by private/ public organizations to improve their service and promptly gau…
Identifying Complaints from Product Reviews: A Case Study on Hindi
Automatic recognition of customer complaints on products or services that they purchase can be crucial for the organisations, multinationals and online retailers since they can exploit this information to fulfil their cu…
Machine TranslationNMTTranslationCRL+: A Novel Semi-Supervised Deep Active Contrastive Representation Learning-Based Text Classification Model for Insurance Data
Financial sector and especially the insurance industry collect vast volumes of text on a daily basis and through multiple channels (their agents, customer care centers, emails, social networks, and web in general). The i…
Active LearningRepresentation Learningtext-classificationText ClassificationA Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods…
Domain AdaptationLanguage ModelingLanguage ModellingMachine Translation+4