No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Text analytics for customer satisfaction prediction: A case study in the banking domain
Abstract
Customer centricity is key to the success of modern business companies. Recently, a lot of attention has been paid on machine learning methods for customer satisfaction analysis and monitoring of trends in customer opinions and sentiments. The current study aims at predicting customer satisfaction from contact center chat services – a domain largely underrepresented in the existing literature devoted on sentiment analysis. Main goal of the current paper is to analyze chat communication between operators in a call center and clients of a large bank and develop a methodology for sentiment analysis based only on chat data. This study is the first explicitly aimed at service rating prediction based only on textual features combined with grammatical information extracted from chats. The proposed approach is purely statistical and does not rely on sentiment lexicons. Drawn are valuable conclusions regarding the usefulness of different feature sets, text normalization techniques and levels of chat data representation. Main practical benefit of analyzing customer satisfaction is that it may lead to large improvement of customer services quality, as well as better understanding of customers’ experience, pain points and needs which underlies its importance in the financial services domain and not only. The study contributes to the literature devoted on practical applications of text analytics in Bulgarian and sentiment analysis for low-resource languages. To the best of the author's knowledge, the current study is the first for this combination of task, language, and data domain. The use case under study is in the banking domain but results and findings might be helpful in any other domain in which similar communication is being analyzed.
... In the banking and financial sector there is several studies applying sentiment analysis techniques to examine the level of perception towards banking products and services [47][48][49][50][51][52][53][54]. For example, Fernandez et al. [55] employed sentiment analysis techniques to create a sentiment index based on tweets in Spanish, with the aim of capturing the perception of risk in Mexico's financial system as reflected on Twitter. ...
... Several studies have explored the application of text mining in various sectors, including financial industry (Hristova, 2022;Kuilboer & Stull, 2021;Pejić Bach et al., 2019), management disciplines Kushwaha et al., 2021), supply chain sector (Chu et al., 2020). However, a limited number of articles utilize text mining for bank bankruptcy prediction. ...
This study aims to investigate the material loss review published by the Federal Deposit Insurance Corporation (FDIC) on 98 failed banks from 2008 to 2015. The text mining techniques via machine learning, i.e. bag of words, document clustering, and topic modeling, are employed for the investigation. The pre-processing step of text cleaning is first performed prior to the analysis. In comparison with traditional methods using financial ratios, our study generates actionable insights extracted from semi-structured textual data, i.e. the FDIC’s reports. Our text analytics suggests that to prevent from being a failure; banks should beware of loans, board management, supervisory process, the concentration of acquisition, development, and construction (ADC), and commercial real estate (CRE). In addition, the primary reasons that US banks went failure from 2008 to 2015 are explained by two primary topics, i.e. loan and management.
Purpose
This study examines the role of online customer reviews through text mining and sentiment analysis to improve customer satisfaction across various services within the UK banking sector. Additionally, the study analyses sentiment trends over a five-year period.
Design/methodology/approach
Using DistilBERT and Support Vector Machine algorithms, customer sentiments were assessed through an analysis of 20,137 Trustpilot reviews of HSBC, Santander, and Tesco Bank from 2018 to 2023. Data pre-processing steps were implemented to ensure data integrity and minimize noise.
Findings
Both positive and negative sentiments provide valuable insights. The results indicate a high prevalence of negative sentiments related to customer service and communication, with HSBC and Santander receiving 90.8% and 89.7% negative feedback, respectively, compared to Tesco Bank’s 66.8%. Key areas for improvement include HSBC’s credit card services and call center efficiency, which experienced increased negative feedback during the COVID-19 pandemic. The findings also demonstrate that DistilBERT excelled in categorizing reviews, while the SVM model, when combined with customer ratings, achieved 96% accuracy in sentiment analysis.
Research limitations/implications
This study focuses on UK bank consumers of HSBC, Santander, and Tesco Bank. A multi-country or cross-cultural study may further enhance our understanding of the approaches and findings.
Practical implications
Online customer reviews become more informative when categorised by service sector. To enhance customer satisfaction, bank managers should pay attention to both positive and negative reviews, and track trends over time.
Originality/value
The uniqueness of this study lies in its exploration of the importance of categorisation in text-mining-based sentiment analysis, its focus on the influence of both positive and negative sentiments, and its emphasis on tracking sentiment trends over time.
Purpose: A variety of soft approaches have already been considered in relation to the growth of marketing. Problems related to customer satisfaction and retention have been studied earlier. The application of business intelligence, artificial intelligence, and data mining has a great impact on the development of business organizations. Customers are increasing day by day in every field, which is complicating the method of finding their satisfaction level. To find the best method to solve these complexities, advanced machine learning approaches can be used. This paper discusses a detailed literature survey of various approaches used to identify customer satisfaction and retention using customer logs in various fields. Design/Methodology/Approach: The details collected for this review paper were obtained by analysing and comparing different research articles from recognized resources. Objective: To find a research gap and appropriate solutions for customer satisfaction accuracy using machine learning approaches. Results/ Findings: Review of this paper gives a proper understanding of customer satisfaction in various domains using machine-learning approaches Originality/Value: The review of this paper gives an analysis of machine learning algorithms for customer satisfaction in various fields and suggests the importance of new classification models. Type of Paper: Literature Review.
Digitalization affects all fields of the modern world including the economic, political, and social aspects of our life. Governments are also involved in this process. Considering the rapid transition towards digital e-services that we evidence since the COVID-19 outbreak, the detection and analysis of public opinion on e-government services becomes even more important. The sentiments and opinions of users on digital public services might be used to foster improvements in the development and implementation of the e-services. In this paper we engage the advances in NLP so as to examine the possibilities to analyze in an automated manner the opinions and sentiments towards e-government services expressed by citizens in various social networks in Bulgaria and this is the main goal of our research. For this purpose, we design an integrated ML-based AI system that aims to support decision makers in e-government and public services provision. The system utilizes a variety of data sources - news websites, web forums and other online social networks. To the best of the authors’ knowledge, this is the first study that develops a methodology for mining public opinion in Bulgaria based on a combination of NLP and ML techniques, rather than relying on surveys or in-depth interviews.
Text analytics is becoming an integral part of modern business and economic research and analysis. However, the extent to which its application is possible and accessible varies for different languages. The main goal of this paper is to outline fundamental research on text analytics applied on data in Bulgarian. A review of key research articles in two main directions is provided – development of language resources for Bulgarian and experimenting with Bulgarian text data in practical applications. By summarizing the results of a large literature review, we draw conclusions about the degree of development of the field, the availability of language resources for the Bulgarian language and the extent to which text analytics has been applied in practical problems. Future directions for research are outlined. To the best of the author’s knowledge, this is the first study providing a comprehensive overview of progress in the field of text analytics in Bulgarian.
The field of sentiment analysis is widely utilized for analyzing the text data and then extracting the sentiment component out of that. The online commercial websites generates a huge amount of textual data via customer’s reviews, comments, feedbacks and tweets every day. Aspect level analysis of this data provides a great help to retailers in better understanding of customer’s expectations and then shaping their policies accordingly. However, a number of algorithms are existing these days to do aspect level sentiment detection on specified domains, but a few consider bipolar words (words which changes polarity according to context) while doing analyses. In this paper, a novel approach has been presented that utilize aspect level sentiment detection, which focuses on the features of the item. The work has been implemented and tested on Amazon customer reviews (crawled data) where aspect terms are identified first for each review. The system performs pre-processing operations like stemming, tokenization, casing, stop-word removal on the dataset to extract meaningful information and finally gives a rank for its classification in negativity or positivity.
Online shopping websites like Amazon stipulate a platform to the users where they can share their opinions about different products. Recently, it has been identified that prior to the purchasing, 81% of the users explore different online platforms in order to assess the reliability of product that they intend to buy. The reviews of different users are expressed by using natural language, which help a user to make an informed decision. From past few years, scientific community has payed attention to automatically specify the meaning of review through Sentiment Analysis. Sentiment Analysis is a research area which is gradually being evolved thus, helping the users to tackle the sentiment hidden in a review. To date, different sentiment analysis-based studies have been conducted in literature. For sentiment classification, the core ingredient is the exploitation of polarity bearing words present in the reviews e.g. adjectives, verbs, and adverbs etc. Different studies suggest the importance of different forms of adverbs in sentiment classification task. In literature, it has been reported that general adverbs strongly help to classify sentiments with better accuracy whereas other suggest that degree adverbs are important for sentiment classification. There are ten distinct forms of adverbs such as general adverbs, general superlative adverbs, general comparative adverbs, general-wh adverbs, degree adverbs, degree superlative adverbs, degree comparative adverbs, degree-wh adverbs, time adverbs and locative adverbs. In this paper, we intend to tackle a question that what is the impact of different forms of adverb on the classification of sentiments? For this, the impacts of all these forms have been evaluated on 51,005 reviews of two products, office products and musical DVDs acquired from Amazon. The outcomes of study revealed that two general superlative adverbs and degree-wh adverb hold more impact than the other forms of adverbs. The general superlative adverbs have attained F-measure of 0.86 and degree-wh adverbs have attained F-measure of 0.80.
Sentiment analysis refers to the algorithmic extraction of subjective information from textual data and—driven by the increasing amount of online communication—has become one of the fastest growing research areas in computer science with applications in several domains. Although sports events such as football matches are accompanied by a huge public interest and large amount of related online communication, social media analysis in general and sentiment analysis in particular are almost unused tools in sports science so far. The present study tests the feasibility of lexicon-based tools of sentiment analysis with regard to football-related textual data on the microblogging platform Twitter. The sentiment of a total of 10,000 tweets with reference to ten top-level football matches was analyzed both manually by human annotators and algorithmically by means of publicly available sentiment analysis tools. Results show that the general sentiment of realistic sets (1000 tweets with a proportion of 60% having the same polarity) can be classified correctly with more than 95% accuracy. The present paper demonstrates that sentiment analysis can be an effective and useful tool for sports-related content and is intended to stimulate the increased use of and discussion on sentiment analysis in sports science.
Nowadays, sentiment analysis is a method used to analyze the sentiment of the feedback given by a user in an online document, such as a blog, comment, and review, and classifies it as negative, positive, or neutral. The classification process relies upon the analysis of the polarity features of the natural language text given by users. Polarity analysis has been an important subtask in sentiment analysis; however, detecting correct polarity has been a major issue. Different researchers have utilized different polarity features, such as standard part-of-speech (POS) tags such as adjectives, adverbs, verbs, and nouns. However, there seems to be a lack of research focusing on the subcategories of these tags. The aim of this research was to propose a method that better recognizes the polarity of natural language text by utilizing different polarity features using the standard POS category and the subcategory combinations in order to explore the specific polarity of text. Several experiments were conducted to examine and compare the efficacies of the proposed method in terms of F-measure, recall, and precision using an Amazon dataset. The results showed that JJ + NN + VB + RB + VBP + RP, which is a POS subcategory combination, obtained better accuracy compared to the baseline approaches by 4.4% in terms of F-measure.
In recent years, there has been an exponential growth in the number of complex documents and texts that require a deeper understanding of machine learning methods to be able to accurately classify texts in many applications. Many machine learning approaches have achieved surpassing results in natural language processing. The success of these learning algorithms relies on their capacity to understand complex models and non-linear relationships within data. However, finding suitable structures, architectures, and techniques for text classification is a challenge for researchers. In this paper, a brief overview of text classification algorithms is discussed. This overview covers different text feature extractions, dimensionality reduction methods, existing algorithms and techniques, and evaluations methods. Finally, the limitations of each technique and their application in the real-world problem are discussed.
Social networks have changed the communication patterns significantly. Information available from different social networking sites can be well utilized for the analysis of users opinion. Hence, the organizations would benefit through the development of a platform, which can analyze public sentiments in the social media about their products and services to provide a value addition in their business process. Over the last few years, deep learning is very popular in the areas of image classification, speech recognition, etc. However, research on the use of deep learning method in sentiment analysis is limited. It has been observed that in some cases the existing machine learning methods for sentiment analysis fail to extract some implicit aspects and might not be very useful. Therefore, we propose a deep learning approach for aspect extraction from text and analysis of users sentiment corresponding to the aspect. A seven layer deep convolutional neural network (CNN) is used to tag each aspect in the opinionated sentences. We have combined deep learning approach with a set of rule-based approach to improve the performance of aspect extraction method as well as sentiment scoring method. We have also tried to improve the existing rule-based approach of aspect extraction by aspect categorization with a predefined set of aspect categories using clustering method and compared our proposed method with some of the state-of-the-art methods. It has been observed that the overall accuracy of our proposed method is 0.87 while that of the other state-of-the-art methods like modified rule-based method and CNN are 0.75 and 0.80 respectively. The overall accuracy of our proposed method shows an increment of 7–12% from that of the state-of-the-art methods.
http://www.bultreebank.org/TechRep/BTB-TR03.pdf
This study investigates factors that may determine satisfaction in customer service operations. We utilized more than 170,000 online chat sessions between customers and agents to identify characteristics of chat sessions that incurred dissatisfying experience. Quantitative data analysis suggests that sentiments or moods conveyed in online conversation are the most predictive factor of perceived satisfaction. Conversely, other session related meta data (such as that length, time of day, and response time) has a weaker correlation with user satisfaction. Knowing in advance what can predict satisfaction allows customer service staffs to identify potential weaknesses and improve the quality of service for better customer experience.
This study investigates factors that may determine satisfaction in customer
service operations. We utilized more than 170,000 online chat sessions between
customers and agents to identify characteristics of chat sessions that incurred
dissatisfying experience. Quantitative data analysis suggests that sentiments
or moods conveyed in online conversation are the most predictive factor of
perceived satisfaction. Conversely, other session related meta data (such as
that length, time of day, and response time) has a weaker correlation with user
satisfaction. Knowing in advance what can predict satisfaction allows customer
service staffs to identify potential weaknesses and improve the quality of
service for better customer experience.
Sentiment Analysis (SA) is an ongoing field of research in text mining field. SA is the computational treatment of opinions, sentiments and subjectivity of text. This survey paper tackles a comprehensive overview of the last update in this field. Many recently proposed algorithms' enhancements and various SA applications are investigated and presented briefly in this survey. These articles are categorized according to their contributions in the various SA techniques. The related fields to SA (transfer learning, emotion detection, and building resources) that attracted researchers recently are discussed. The main target of this survey is to give nearly full image of SA techniques and the related fields with brief details. The main contributions of this paper include the sophisticated categorizations of a large number of recent articles and the illustration of the recent trend of research in the sentiment analysis and its related areas.
The paper starts with an overview of the most important approaches to stemming for English as well as for some Slavic languages. Then, the design, implementation and evaluation of an inflectional stemmer for Bulgarian are described. The problem is addressed as a machine-learning task from a large morphological dictionary. A detailed automatic evaluation for different parameter values in terms of under-stemming, over-stemming and coverage is provided.
The paper starts with an overview of some important approaches to stemming for English and other languages. Then, the design, implementation and evalua- tion of the BulStem inflectional stemmer for Bulgarian are presented. The problem is addressed from a machine- learning perspective using a large morphological dictio- nary. A detailed automatic evaluation in terms of under- stemming, over-stemming and coverage is provided. In addition, the effect of stemming and BulStem parameters setting is demonstrated on a particular task: text catego- risation using kNN+LSA.
This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not rec- ommended (thumbs down). The classifi- cation of a review is predicted by the average semantic orientation of the phrases in the review that contain adjec- tives or adverbs. A phrase has a positive semantic orientation when it has good as- sociations (e.g., "subtle nuances") and a negative semantic orientation when it has bad associations (e.g., "very cavalier"). In this paper, the semantic orientation of a phrase is calculated as the mutual infor- mation between the given phrase and the word "excellent" minus the mutual information between the given phrase and the word "poor". A review is classified as recommended if the average semantic ori- entation of its phrases is positive. The al- gorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations). The ac- curacy ranges from 84% for automobile reviews to 66% for movie reviews.
In this work we present SENTIWORDNET 3.0, a lexical resource explicitly devised for supporting sentiment classification and opinion mining applications. SENTIWORDNET 3.0 is an improved version of SENTIWORDNET 1.0, a lexical resource publicly available for research purposes, now currently licensed to more than 300 research groups and used in a variety of research projects worldwide. Both SENTIWORDNET ...
Scikit-learn is a Python module integrating a wide range of state-of-the-art
machine learning algorithms for medium-scale supervised and unsupervised
problems. This package focuses on bringing machine learning to non-specialists
using a general-purpose high-level language. Emphasis is put on ease of use,
performance, documentation, and API consistency. It has minimal dependencies
and is distributed under the simplified BSD license, encouraging its use in
both academic and commercial settings. Source code, binaries, and documentation
can be downloaded from http://scikit-learn.sourceforge.net.
We develop fast algorithms for estimation of generalized linear models with convex penalties. The models include linear regression, two-class logistic regression, and multi- nomial regression problems while the penalties include âÂÂ_1 (the lasso), âÂÂ_2 (ridge regression) and mixtures of the two (the elastic net). The algorithms use cyclical coordinate descent, computed along a regularization path. The methods can handle large problems and can also deal efficiently with sparse features. In comparative timings we find that the new algorithms are considerably faster than competing methods.
Quality assurance (QA) and customer satisfaction (C-Sat) analysis are two commonly used practices to measure goodness of dialogues between agents and customers in contact centers. The practices however have a few shortcomings. QA puts sole emphasis on agents’ organizational compliance aspect whereas C-Sat attempts to measure customers’ satisfaction only based on post dialogue surveys. As a result, outcome of independent QA and C-Sat analysis may not always be in correspondence. Secondly, both processes are retrospective in nature and hence, evidences of bad past dialogues (and consequently bad customer experiences) can only be found after hours or days or weeks depending on their periodicity. Finally, human intensive nature of these practices lead to time and cost overhead while being able to analyze only a small fraction of dialogues. In this paper, we introduce an automatic real-time quality assurance system for contact centers — QART (pronounced cart). QART performs multi-faceted analysis on dialogue utterances, as they happen, using sophisticated statistical and rule-based natural language processing (NLP) techniques. It covers various aspects inspired by today’s QA and C-Sat practices as well as introduces novel incremental dialogue summarization capability. QART front-end is an interactive dashboard providing views of ongoing dialogues at different granularity enabling agents’ supervisors to monitor and take corrective actions as needed. We demonstrate effectiveness of different back-end modules as well as the overall system by experimental results on a real-life contact center chat dataset.
This paper presents an approach for prediction of results for sport events. Usu-ally the sport forecasting approaches are based on structured data.We test the hypothesis that the sports results can be predicted by using natural language processing and machine learning techniques applied over interviews with the players shortly before the sport events. The pro-posed method uses deep learning contextual models, applied over unstructured textual documents. Several experiments were performed for interviews with players in individual sports like boxing, martial arts,and tennis. The results from the conducted experiment confirmed our initial assumption that an interview from a sportsman be-fore a match contains information that can be used for prediction the outcome from it.Furthermore, the results provide strong evidence in support of our research hypothesis, that is, we can predict the outcome from a sport match analyzing an interview,given before it
Sentiment analysis in dialogues plays a critical role in dialogue data analysis. However, previous studies on sentiment classification in dialogues largely ignore topic information, which is important for capturing overall information in some types of dialogues. In this study, we focus on the sentiment classification task in an important type of dialogue, namely customer service dialogue, and propose a novel approach which captures overall information to enhance the classification performance. Specifically, we propose a topic-aware multi-task learning (TML) approach which learns topic-enriched utterance representations in customer service dialogue by capturing various kinds of topic information. In the experiment, we propose a large-scale and high-quality annotated corpus for the sentiment classification task in customer service dialogue and empirical studies on the proposed corpus show that our approach significantly outperforms several strong baselines.
As the prevalence of social media on the Internet, opinion mining has become an essential approach to analyzing so many data. Various applications appear in a wide range of industrial domains. Meanwhile, opinions have diverse expressions which bring along research challenges. Both of the practical demands and research challenges make opinion mining an active research area in recent years. In this paper, we present a review of Natural Language Processing (NLP) techniques for opinion mining. First, we introduce general NLP techniques which are required for text preprocessing. Second, we investigate the approaches of opinion mining for different levels and situations. Then we introduce comparative opinion mining and deep learning approaches for opinion mining. Opinion summarization and advanced topics are introduced later. Finally, we discuss some challenges and open problems related to opinion mining.
With the rapid growth of social media, sentiment analysis, also called opinion mining, has become one of the most active research areas in natural language processing. Its application is also widespread, from business services to political campaigns. This article gives an introduction to this important area and presents some recent developments.
A single phone call can make or break a valuable customer-organization relationship. Maintaining good quality of service can lead to customer loyalty, which affects profitability. Traditionally, customer feedback is mainly collected by interviews, questionnaires, and surveys; the major drawback of these data collection methods is in their limited scale. The growing amount of research conducted in the field of sentiment analysis, combined with advances in text processing and Artificial Intelligence, has led us be the first to present an intelligent system for mining sentiment from transcribed utterances—wherein the noisiness property and short length poses extra challenges to sentiment analysis. Our aim is to detect and process affective factors from multiple layers of information, and study the effectiveness and robustness of each factor type independently, by proposing a tailored machine learning paradigm. Three types of factors are related to the textual content while two overlook it. Experiments are carried out on two datasets of transcribed phone conversations, obtained from real-world telecommunication companies.
In order to assure and to improve the quality of service, call center operators need to automatically identify the problematic calls in the mass of information flowing through the call center. Our method to select and rank those critical conversations uses linguistic text mining to detect sentiment markers on French automatic speech transcripts. The markers' weight and orientation are used to calculate the semantic orientation of the speech turns. The course of a conversation can then be graphically represented with positive and negative curves. We have established and evaluated on a manually annotated corpus three heuristics for the automatic selection of problematic conversations. Two proved to be very useful and complementary for the retrieval of conversations having segments with anger and tension. Their precision is high enough for use in real world systems and the ranking evaluated by mean precision follows the usual relevance behavior of a search engine.
The authors identify specific customer orientation behaviors (COBs) of call center employees and show that these behaviors relate to customer evaluations of service quality. Using qualitative, inductive analyses of 166 telephone service interactions in a retail bank call center, they identify five types of COBs associated with helping customers. The COBs are (a) anticipating customer requests, (b) offering explanations/justifications, (c) educating customers, (d) providing emotional support, and (e) offering personalized information. Using deductive analyses, the authors show that customers rate the quality of service interactions higher when service providers employ COBs. The qualitative findings contribute to the understanding of the specific employee behaviors associated with service quality, and the quantitative findings validate the importance of these behaviors.
This study investigated the potential benefits of employ- ees' customer orientation to service providers. To achieve that aim, the author tested relationships between cus- tomer focus (creating value for customers) and customer feedback (seeking evaluations of work and quality) and perceived service quality and customers' affective com- mitment and loyalty to service firms. Mail survey data were collected from customers of two call centers in Australia. The samples consisted of end "consumers" of insurance services (n = 289) and business "customers" of a bank (n = 325). Two key findings emerged from the final structural model. First, customer focus was related to loy- alty, with partial mediation by perceived service quality. Second, and in contrast, customer feedback exhibited a direct relationship only to affective commitment. The find- ings were highly consistent for the two samples and have implications for both managers and researchers.
An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area, of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object. This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. Our focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. We include material on summarization of evaluative text and on broader issues regarding privacy, manipulation, and economic impact that the development of opinion-oriented information-access services gives rise to. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided.
We consider the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative. Using movie reviews as data, we find that standard machine learning techniques definitively outperform human-produced baselines. However, the three machine learning methods we employed (Naive Bayes, maximum entropy classification, and support vector machines) do not perform as well on sentiment classification as on traditional topic-based categorization. We conclude by examining factors that make the sentiment classification problem more challenging.
Fine-grained sentiment analysis for movie reviews in Bulgarian
- B Kapukaranov
- P Nakov
B. Kapukaranov and P. Nakov, "Fine-grained sentiment analysis for movie reviews in Bulgarian," in
Proceedings of the International Conference Recent Advances in Natural Language Processing, pp. 266-274,
(2015).
Leveraging part-of-speech tagging for sentiment analysis in short texts and regular texts
- W H Khong
- L K Soon
- H N Goh
- S C Haw
W. H. Khong, L. K. Soon, H. N. Goh and S. C. Haw, "Leveraging part-of-speech tagging for sentiment
analysis in short texts and regular texts," in Joint International Semantic Technology Conference, pp. 182-197,
(2018).
Bert: Pre-training of deep bidirectional transformers for language understanding
- J Devlin
- M W Chang
- K Lee
- K Toutanova
J. Devlin, M. W. Chang, K. Lee and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for
language understanding," preprint arXiv:1810.04805, (2018).
A review of natural language processing techniques for opinion mining systems
- S Sun
- C Lou
- J Chen
S. Sun, C. Lou and J. Chen, "A review of natural language processing techniques for opinion mining systems,"
Information fusion, vol.36, pp. 10-25, (2017).
BulStem: Design and evaluation of inflectional stemmer for Bulgarian
- P Nakov
P. Nakov, "BulStem: Design and evaluation of inflectional stemmer for Bulgarian," in Workshop on Balkan
Language Resources and Tools (Balkan Conference in Informatics), (2003).
- K Simov
- P Osenova
- M Slavcheva
K. Simov, P. Osenova and M. Slavcheva, "BTB-TR03: BulTreeBank Morphosyntactic Tagset," BTB-TS
version 2.0. Technical report, Bulgarian Academy of Sciences, Sofia, Bulgaria, (2004).