Using deep learning to enhance business intelligence in organizational management (original) (raw)
Related papers
Sentiment Analysis for Recommendation System and Business Intelligence using Deep Learning
2021
Sentiment analysis (SA) is the study of analyzing the sentiments, impressions by people about entities, persons, topics and services. Sentimental analysis uses text analysis techniques from big data analytics. Nowadays most of the people are active on social media. They usually show their sentiments through different websites or platforms. These sentiments are most important for business streams. In today’s world, sentimental analysis is becoming important for identifying hidden information in unstructured data formats that arise in the usage of various platforms for business sides. Deep learning plays an important for this business intelligence. The sentiment analysis by deep learning uses popular algorithms. So, in this document we will see how deep learning is important for recommendation system and business intelligence using sentimental
Global Business Review, 2019
First mover advantage does not go to the first company that launches, it goes to the first company that scales' (Reid Hoffman, co-founder of LinkedIn, ScaleIt, 2016). M. Andreesen defines scale-up as a company that has identified its product/market fit and has reached notable proofs of market traction (e.g., profitability, revenues, active users, registered users, market demand). It has been previously established that five interdependent core dimensions can be used to evaluate scale-up: customer, product, team, business model and financials. Most of the business failures result from falling apart of one or more of these dimensions with others. We in our article discuss the 'customer dimension' as the essence of scaling up. For running a profitable business, it is crucial to evaluate customers' reviews, like their perception and expectation from the product and services in terms of service quality, deliverables, staff and management practices and pricing. This will increase customer satisfaction which will further boost the demand and popularity of the brand and business. The customers today are very vocal in sharing their experiences through social media blogs, channels, review sites and so on. These experiences need to be decrypted by the management to understand the customer's point of view, their apprehensions and expectations. Sentiment analysis is one of the best ways to tap customer feedback. The usual way of analysis involves the bag of words model using ngrams. A more refined version is an ontology-based analysis. Research has also been done using the radial basis function kernel for support vector machines (SVMs) (for recognizing polarity of sentiments). Naïve Bayes algorithms have also been used in some sentiment studies along with linear kernel SVM classifiers. But we realized during the literature review that it is not enough to just classify the text into positive and negative or a few more categories. It is even more important to know which topics are being discussed by the customers, their intention behind the message and further the need to classify them as complaints, suggestions, appreciation or query and so on. Thus, we in our article discuss the solution to all these types of analyses using 'deep sentiment analysis'. We discuss the case of a few current social topics and introduce 'recurrent neural networks' (RNNs) and 'convolutional neural networks' (CNNs) for sentiment and intent analysis.
Sentiment Analysis: A comparative study of Deep Learning and Machine Learning
IRJET, 2022
As the population of customers grows, it becomes increasingly tedious to analyze customer feedback. By 2025 it is estimated that more than 75% of the data relating to customer reviews will be unstructured, meaning that the challenges to analyze and gain insights from these reviews will increase. With help of sentiment analysis by machine learning or deep learning, data gathered via reviews can be categorized under the labels of positive, negative and neutral. Sentiment analysis makes it convenient to understand the customer's mindset and preferences, assisting companies in changing their strategies and products to better cater the needs of their customer base.
Deep Learning Based Sentiment Classification on User-Generated Big Data
Recent Advances in Computer Science and Communications, 2019
Background: Sentiment analysis of big data such as Twitter primarily aids the organizations with the potential of surveying public opinions or emotions for the products and events associated with them. Objective: In this paper, we propose the application of a deep learning architecture namely the Convolution Neural Network. The proposed model is implemented on benchmark Twitter corpus (SemEval 2016 and SemEval 2017) and empirically analyzed with other baseline supervised soft computing techniques. The pragmatics of the work includes modelling the behavior of trained Convolution Neural Network on wellknown Twitter datasets for sentiment classification. The performance efficacy of the proposed model has been compared and contrasted with the existing soft computing techniques like Naïve Bayesian, Support Vector Machines, k-Nearest Neighbor, Multilayer Perceptron and Decision Tree using precision, accuracy, recall, and F-measure as key performance indicators. Methods: Majority of the st...
Nowadays, a rising number of individuals use online social networks, e-commerce, and applications to not only socialize and engage, but also to express their ideas. Deep Learning is an area of machine learning dealing with neural representations of procedures, most frequently shown as neural networks, neural beliefs, and so on. When evaluating sentiments for a given datasets, it is critical to choose the most practical and precise approach possible because this impacts both buyers and sellers. Deep Learning (DL) approaches have been used to identify important data and make recommendations from enormous data sets. The effectiveness and results of various deep learning techniques may change based on the data sets utilized, as well as the techniques' appropriateness to the information and applications domains under discussion. To meet this demand, a comparative examination of well-known deep learning techniques was conducted. E-commerce was the first business to capitalize on the advantages of Deep Learning (DL). Firms now have whole DL departments, which is not uncommon. Because digital transactions have become the usual means of acquiring products and services, top E-commerce businesses are investigating how DL may improve customer satisfaction and company profitability. The idea is that they contain a massive volume of information, and making use of that information is difficult. E-commerce firms spend a lot of money to automating tedious procedures, enhance the customer experiences, tailor offers for specific customers, and gain a deeper understanding of their customers.
Using Deep Learning Networks to Predict Telecom Company Customer Satisfaction Based on Arabic Tweets
2019
Information systems are transforming businesses, which are using modern technologies towards new business models based on digital solutions, which ultimately lead to the design of novel socioeconomic systems. Sentiment analysis is, in this context, a thriving research area. This paper is a case study of Saudi telecommunications (telecom) companies, using sentiment analysis for customer satisfaction based on a corpus of Arabic tweets. This paper compares, for the first time for Saudi social media in telecommunication, the most popular machine learning approach, support vector machine (SVM), with two deep learning approaches: long short-term memory (LSTM) and gated recurrent unit (GRU). This study used LSTM and GRU with two different implementations, adding attention mechanism and character encoding. The study concluded that the bidirectional-GRU with attention mechanism achieved a better performance in the telecommunication domain and allowed detection of customer satisfaction in the telecommunication domain with high accuracy.
Sentiment Analysis Based on Deep Learning: A Comparative Study
Electronics, 2020
The study of public opinion can provide us with valuable information. The analysis of sentiment on social networks, such as Twitter or Facebook, has become a powerful means of learning about the users’ opinions and has a wide range of applications. However, the efficiency and accuracy of sentiment analysis is being hindered by the challenges encountered in natural language processing (NLP). In recent years, it has been demonstrated that deep learning models are a promising solution to the challenges of NLP. This paper reviews the latest studies that have employed deep learning to solve sentiment analysis problems, such as sentiment polarity. Models using term frequency-inverse document frequency (TF-IDF) and word embedding have been applied to a series of datasets. Finally, a comparative study has been conducted on the experimental results obtained for the different models and input features.
Customer Reviews’ Sentiments Analysis using Deep Learning
International Journal of Computer Applications, 2020
In this era of digitalization, Sentiment Analysis(SA) has become a necessity for progress and prosperity in marketing. Sentiment analysis has become a powerful way of knowing the opinions and thoughts of users. The viewpoint of the consumer, such as knowledge sharing would include a lot of useful experience, while one wrong idea will cost too much for the company.SA has many social media data-related problems, such as natural language interpretation, etc. Issue of theory and technique also affect the accuracy of detecting the polarity. There is a problem of text classification such as analysis of sentiments in document level, sentence level, feature based. Document level analysis is done by two approaches: supervised learning and unsupervised learning. Sentence level contains sentences containing opinions. Aspect based analysis have different attributes is performed in customer reviews. Product opinion is taken for knowing the sentiments. Opinions are compared and are extracted as a feature.SA is very important for business purpose because it gives the way for improving their operations and the products they offer. For improving business strategy it plays an important role. It provides many key benefits like impactful decisions, for finding relevant products, improving business strategy, beating competitions, tackling positive or negative issues affecting the product. To overcome such issues, deep learning processes are applied. The work focuses on two main tasks. Firstly, to extract sentiments present in data of social media of customers' reviews and secondly, to use the deeplearning process for the sentiments' extraction for customer reviews.
Text mining based sentiment analysis using a novel deep learning approach
International Journal of Nonlinear Analysis and Applications, 2021
Leveraging text mining for sentiment analysis, and integrating text mining and deep learning are the main purposes of this paper. The presented study includes three main steps. At the first step, pre-processing such as tokenization, text cleaning, stop word, stemming, and text normalization has been utilized. Secondly, feature from review and tweets using Bag of Words (BOW) method and Term Frequency _Inverse Document Frequency is extracted. Finally, deep learning by dense neural networks is used for classification. This research throws light on understanding the basic concepts of sentiment analysis and then showcases a model which performs deep learning for classification for a movie review and airline$_$ sentiment data set. The performance measure in terms of precision, recall, F1-measure and accuracy were calculated. Based on the results, the proposed method achieved an accuracy of 95.3895.38%95.38 and 93.8493.84%93.84 for a movie review and Airline$_$ sentiment, respectively.
A simplified classification computational model of opinion mining using deep learning
International Journal of Electrical and Computer Engineering (IJECE), 2024
Opinion and attempts to develop an automated system to determine people's viewpoints towards various units such as events, topics, products, services, organizations, individuals, and issues. Opinion analysis from the natural text can be regarded as a text and sequence classification problem which poses high feature space due to the involvement of dynamic information that needs to be addressed precisely. This paper introduces effective modelling of human opinion analysis from social media data subjected to complex and dynamic content. Firstly, a customized preprocessing operation based on natural language processing mechanisms as an effective data treatment process towards building quality-aware input data. On the other hand, a suitable deep learning technique, bidirectional long short term-memory (Bi-LSTM), is implemented for the opinion classification, followed by a data modelling process where truncating and padding is performed manually to achieve better data generalization in the training phase. The design and development of the model are carried on the MATLAB tool. The performance analysis has shown that the proposed system offers a significant advantage in terms of classification accuracy and less training time due to a reduction in the feature space by the data treatment operation.