Tracking how a change in a service affects Telecom Customers feeling using Sentiment Analysis ‘Naïve Bayes’
Description & MotivationContext ProblemTracking the effect of change a service on the teleco customer feeling is very important analysis for Teleco Companies. In this trial, machine learning was combined to natural language processing and personality insights in the process of pre-learning of teleco customer Sentiment Analysis.
Need MotivationThis research is done to achieve teleco customer sentiment analysis in changing a service with accuracy of 92% using the teleco AI chat bot.
Task ContributionA combination among four stages of personality insights, natural language processing, sentiment analysis and chat bot system is created to achieve the needed task.
Object What paper tries to coverThis paper covers the effect of combining the personality insights in the natural language processing pre learning stage on sentiment analysis.
OutcomeResults findingsThe proposed solution achieved accuracy of 92% of the case of the telco companies produce a new service or change in the current service.
Conclusion and recommendations interpretation of the findingsCombining the machine learning technique in the natural language processing and personality insights pre learning stage and adding a feedback using the obtained results achieve higher accuracy than using the traditional sentiment analysis techniques.
Perspectives FutureIt is planned to use Hybrid Machine learning and deep learning techniques instead of using Naïve Bayes alone to make use of the higher performance in the learning process.
IntroductionContext ProblemWith the growth of teleco companies such as Etisalat ,Orange, Vodafone and We, this are cause of increasing the teleco customer data. Computational linguists have taken advantage of these data, mostly addressing prediction tasks such as sentiment analysis, personality detection and emotion detection. A few works have also been devoted to predicting what the customer filling about the new service. Prediction tasks have many useful applications ranging from tracking opinions about service to identifying the best and bad service and predicting of the teleco customer satisfaction and so on.
The sentiment Analysis is the process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer’s attitude towards a particular topic, service, etc. is positive, negative, or neutral. As the business changes so does the customer sentiment. Publishing a marketing campaign or press release, changing your service or price structure can have an effect. Tracking customer sentiment can measure this. “The IBM Watson Personality Insights service uses linguistic analytics to extract a spectrum of cognitive and social characteristics from the text data that a person generates through blogs, tweets, forum posts, and more.”
ML sentiment analysis and personality insights are the branches of science interested in automating logical decision making, emotional detection, personality detection and customer needs in the teleco customer’s conversation.
What is the problem?Telecom companies get a bad rap when it comes to customer experience. All too often, clients feel that service falls short of their expectations, and that complaints seem to be falling on deaf ears. Yet despite poor customer sentiment, few telecom companies have made customer centricity a priority. So in this paper we need to show how the using of customer textual data that come from some tools such as Ai chat bot help on determine if the teleco customers are willing or not with the new service, if not, how we can help them?, what is the percentage of success and accept the new service. So we can help the teleco companies to live day per day with its customers. If you know aspects and themes in each response, you can also answer questions like: For how long do people react negatively to a change in a service, or do they really love the new feature added? In now a day we observe the increase of teleco companies so, how can we help teleco companies to prevent its customer from leaving it to another teleco company because of the bad of service?
Why is it important?By analyzing the sentiment more accurately, and in particular finding the services that teleco customer are really unhappy about, you can :Focus more on what will make a difference.
Help users to find what they needs, help increasing teleco customers satisfaction.
Help Teleco Company to produce the best service for its customers.
Help Teleco Company for improve its customer care by keep track what the percentage of acceptance that the new service generates.
If you know aspects and themes in each response, you can also answer questions like: For how long do people react negatively to a change in a service, or do they really love the new feature added?
The most effective initial therapy for patients with this disorder occurs if it is detected in the early 20 days. With this in mind that the symptoms of this disease are the same as with other 3 not dangerous ones, people ignoring rate for the symptoms is high. So detecting the disease automatically from its skin symptoms using accurate image processing is a vital process to give early warnings before it gets dangerous.
Need MotivationOver the past 10 years, there were some partially successful trials for helping teleco companies using online social media. Recent research works by (Wollan and Smith, 2010; Barlow and Thomas, 2011; Qualman, 2009; Safko, 2010) corroborate the exponential growth of social media as a new strategic asset for businesses. In particular, (Barker, 2008; Sinderen and Almeida, 2011; Weber, 2009; Gillin and Schwartzman, 2011) enumerate some of the ways social media can be put to use by businesses. effect to be 75%. Researcher name tried mixing drug A with drug B to get positive responses out of the newly formed chemical with a success percentage of 60%. Also Researcher name followed the named techniques algorithms to solve this issue with accuracy increase of 5% greater than another researcher name.
Most of the last related researches try to use the statistical measuring for helping the teleco companies to understand its customer (M Dachyar, A Rusydina 2015; )Nowadays
The problem entities are how understand and use the personality insights values, the sentiment analysis, emotional values of the teleco customers after changing a service to determine the success of the service and willing of the customers about it, how the success of change in a service can see in customer conversation text as we know that “The pen is mightier than the sword”, but most of teleco companies interest in using the statistical analysis to understand its customer instead of customer conversation analysis and personality understanding. What we are trying to do is to automatically recognize the feeling of the telco customer using a mix of personality insights analysis and some sort of ML sentiment analysis, NLP and textual AI algorithms. Doing the automatic recognition of the teleco customer sentiment is expected to increase the efficiency to be higher than 80%.
What we have (Background Sample Review)What we wantTask Contribution
The assumption behind this methodology is that Textual data especially those expressing concerns, frustrations and acceptance from customers are rich in knowledge which needs to be mined for insights. Sentiment analysis is based on categorizations of particular words as ‘positive’ or negative. Algorithms based on presenting conversations in response to such emotional words have to be ‘trained’ on this data. For sentiment analysis in particular, there are many issues with training data, because the procedure depends on the assumption that words are most often associated with particular feelings. Sentiment analysis algorithms can have difficulty identifying when a word is used sarcastically, for example ,Sentiment analysis, unlike classical text mining which focuses on topical words, picks only sentiment signals for real time analysis (Pang and Lee, 2008).
On the other hand a common assumption is that personality traits act like metabolic set points. People may stray briefly from their biological propensity, but they will then tend to drift back to their genetically driven set point. Under these types of models, one would expect to find a negative or null association between time and mean-level change, because any change will represent short-term fluctuations that disappear as people return to their biologically driven set point (Brent W. Roberts and Daniel Mroczek, 2008). The proposed system is built over a state of the art machine learning algorithm used for learning process of sentiment analysis. It is developed by combining these three factors: (1) text preprocessing, (2) sentiment analysis, (3) personality insights analysis and (4) chat bot system is created to achieve the needed task
Object What paper tries to coverWe take the textural data from chat bot teleco customer conversations, passing it through set of NLP algorithms, for eliminating the stop words, computing bag of words and set of text preprocessing, then we can passing it to the pre trained naïve bays classifier for identify the customer sentiment, on the other hand we use the IBM personality insights API for computing the customer big five traits, feeding the two result to a pre trained ML algorithm will increase the accuracy to reach to values higher than 90%.we will discuss this in detail, then we can use all of this results for helping teleco customers get what they need.
Roadmap (Paper Structure)Measuring teleco customer satisfaction and its relationship towards teleco services is now an integral part of our lives. Recent research works by(M Dachyar, A Rusydina, 2015 ; Sujata Joshi 2014; Balakumar Vijayaraman, Swarnalatha Chellappa, 2016 ), Investigating the Customer Care (Mustafa Boroumandzadeh, Mohammad Reza Mirsarraf , Ali Movaghar ), Sentiment analysis has gain much attention in Investigating the customer care in recent years(Sampriti Sarkar, 2018 ; Stephen Nabareseh,Eric Afful-Dadzie, Petr Klímek, Zuzana Kominkova Oplatkova ,2014 ; ), nowadays if you need to understand the customer personality you may use the personality insights that made a change from one person to another (Brent W. Roberts and Daniel Mroczek, 2009 ; ), we found that customer traits relate to the display of positive emotions by the service provider et la (Hwee Hoon Tan, Maw Der Foo, and Min Hui Kwek, 2017), for computing the telceco customer personality traits we will use the IBM personality insights service and sentiment analysis (Mika V.Mäntylä Daniel Graziotin, Miikka Kuutila, 2017) to identify the teleco customer felling after changing a service.
We used a dataset of more than 15000 labeled conversations, comments and posts that have about 55% of the dataset have positive meaning and 45% have a negative meaning. This dataset was collected from (Nabil et al., 2015)1 (Abdulla et al., 2013)2 (Mourad and Darwish, 2013) 3 (Aly and Atiya, 2013) 4 (Banea et al., 2010)5.
Naive Bayes is a useful technique to apply in text classification problems. So we used the naïve Bayes classification algorithm in sentiment analysis that gives accuracy that may reach to 90%. But if we used the personality traits result with it we will reach to accuracy increasing than 92%. But first for moving the text through Naïve bayes we must pass it through textural preprocessing such as using NLP for computing the Bag of words (Maria Carolina Monard, 2006).