Free Essay

Text Mining

In: Other Topics

Submitted By sukriti20
Words 1373
Pages 6
ANALYSING CUSTOMER EXPERIENCE FEEDBACK USING TEXT MINING: A LINGUISTICS-BASED APPROACH
Car park and transfer case study at an airport

21 March 2014

Francisco Villarroel Dr Charalampos Theodoulidis Dr Jamie Burton Prof Thorsten Gruber Dr Mohamed Zaki

Content
• Customer Feedback and Value co-creation • (Text Mining and its applications) • Car park and transfer case study at an airport • Results • Managerial Implications • Further Research

Customer Feedback
“Customer feedback process” plays a key role in ensuring that information from complaints, compliments, market research and other sources are systematically collected, analysed, and disseminated in ways that will drive service improvements” (Lovelock and Wirtz, 2007).

“Service Quality (SQ) is a marketing stream that considers customer feedback as an opportunity for assessing customer (di)satisfaction. SQ can be “measured through the difference between customer expectations and their real experience with the service” (Parasuraman et al.1985).

Customer Feedback Process

Implicit

Explicit

Determined Actions (i.e. eye tracking, reading time, number of scrolling, etc.)

Platforms (e.g. surveys, e-mails, online review, blog, etc.)

Customer Feedback Process
• Many companies analyse explicit feedback using quantitative

methods because of simplicity in analysis
• Evaluating an entire service of quantitative measures will result in

an
• incomplete understanding of customer experience (Macdonald

et al. 2011; Vargo et al. 2007)
• only superficial information about the entire customer

experience (Caemmerer and Wilson 2010)
• not capture all the resources and activities involved (Gronroos

2012)

Compliments and Complaints NOTES
Compliments
• Affects positively front line employees • Promotes positive WOM across

Complaints
• Valuable information about what should

be improved.
• Delight in the case of good service

customers

• Provide information about core

recovery.
• Maintain long term value from

competences of the company

dissatisfied customers.
• Represent areas that does not need

improvements.
• Lack of Originality in their content. • Receive less attention from customer

• Can damage self confidence on front

line employees.
• Can generate negative WOM

managers.
Luthans, (2002); Kraft and Martin, (2001); Soderlund, (1998); Gruber, (2010); Chebat et al (2005); Buttle and Burton, (2002)

Co-creation
What’s Value co-creation?:
• It’s the process of interactions between

the customer and the company’s service proposition.
• It’s a form of understanding the customer and

http://www.brsglobal.com/tag/ikea/

the firm as sum of resources which constantly interact in order to generate value (Vargo and Lush, 2004)
• These interactions occurs across a

service process, through different

activities which start from the contact of the customer with the firm until the end of the service (Payne et al 2008)

http://freshome.com/2008/08/05/ikea-catalog-2009-now-available-online-here

Text Mining
• Process of analyzing collections of textual materials in order to

capture key concepts & themes & uncover hidden trends.
• 80% of firms information is stored in text format.(Ur-Rahman and

Harding 2011)
• The approaches covered in literature:
• Linguistic approach: consider the natural language characteristics of the text in the

documents (e.g., syntax, grammar)
• Non-linguistic approach: view documents as a series of characters, words, sentences, paragraphs. Counting the number of times specific words appear in a document

Objectives
1. Automate process of customer feedback analysis

through a text mining model.
2. Determine what are the most important resources and

activities for the customer when using this service.
3. Evaluate the potential of customer compliments and

complaints for improving their service experience.

Research Process
1. Understand the customer feedback process 2. Collect a sample of customer compliments and complaints. 3. Development and test of a text mining model 4. Present the results to the participant company and evaluate

Customer Feedback Process
• Daily online survey is sent to customers who parked

their car 2 days before.
• In the Survey, open question asking:

“What is the single most important factor you feel we can improve upon to enhance your car park experience”
• The company receives approximately 1000 comments

per week, 50,000 responses annually on average

Current Practice
1. Each comment is classified into just one category (despite often

including more than one compliment, complaint, or suggestion)
2.

Positive or negative sentiments are individual categories, with no relationship to a specific element of the service The classification of comments by means of manual annotation is not consistent (approximately 2 weeks to generate a report)

3.

Proposed Linguistic- based Text Mining
Sample 100 comments

Population

1092 comments

Sample Process
Preprocessing tasks

Sample of 100 comments: • Extract the sentences with more valuable information for The M.A.

Library of Concepts

Categorization of Concepts
Comment
Car Ratin Park g Single improvement factor Barrier did not recognise my prebooked credit card press buzzer but person very helpful bus going out was fine waiting 15mins for bus very poor

Pattern Development

Model

Results and Model Refinement

Barrier did not recognise my pre-booked credit card had to press buzzer but person very helpful. Bus going out was fine - after waiting 15mins for bus on return we walked - very poor

E

5

Text Mining Process
Preprocessing tasks

Library of Concepts

Categorization of Concepts

Sample 100 comments: • Extraction of the main concepts by sentence • Categorization of the concepts into 4 main Groups: Resource Company, Resource Customer, Activities, and Attributes

Pattern Development

Resource Resource company Customer

Barrier credit card Buzzer/ Person bus bus 15 mins

Activity 1

Activity 2 Opinion

C&C Complaint

did not recognise Pre-­‐booked press going out waiting

Model

very helpful Compliment fine Compliment Complaint very poor Complaint

Results and Model Refinement

Text Mining Process
Preprocessing tasks

Sample 100 comments: • Extraction of the most common sentences patterns for compliments and complaints

Library of Concepts

Categorization of Concepts
• Barrier did not recognize my pre-booked credit card
CR Act CuR

Pattern Development

“Complain about entrance”
• …had to press buzzer but person very helpful
CR CR ATP

Model
Act

“Compliment staff”
• Waiting 15 mins for bus
CuR CR

Results and Model Refinement

“Bus Complaint”

Car park-transfer service process

Based on Payne et al (2008); Vargo and Lush (2004)

Text Mining Process
Preprocessing tasks

• The model has in total : • 694 patterns arose from these comments • 47 Subcategories of parking and transfer service process • 678 concepts mapped to these subcategories • 92% overall accuracy

Library of Concepts

Categorization of Concepts

Pattern Development

Model

Evaluation and Refinement

Right Predictions
Compliments vs. Complaints
Complaints Compliments

Implications:
• Considering that the questions was asking about suggestions or complaints it was interesting to find complimenting customers.

14%

86%

Complaints
Complaints through the Service
Most of the complaints were when the customers were inside the Car Park trying to park their car. 87 54 Arriving Car Park Parking Car 298 111

Booking

Bus Service

Compliments
In the case of Bus Service Most of Compliments were Related with the bus driver Helpfulness and Friendliness of staff was found valuable for Customers For general compliments it would be possible to sub-divide into new categories

Compliments
Bus Service Staff 8% 22% 70% General

Overall Results
Service Process Booking
-Booking general -Price

Right Predictions 87 23 64 54 298 71 25 9 111 65 17 111 550

Arriving Car Park Parking Car
-Space

-Staff
-Facilities -Directions -Others Car Park -Others Customer Resources

Bus Service TOTAL

Service Process General Bus Staff TOTAL

Right Predictions 62 7 20 89

Complaints Wrong Predictions Total 3 1 2 1 38 3 4 0 3 12 16 3 45 Compliments Wrong Predictions Total 7 1 2 10

Accurancy 90 24 66 55 336 74 29 9 114 77 33 114 595 97% 96% 97% 98% 89% 96% 86% 100% 97% 84% 52% 97% 92%

Accurancy 69 8 22 99 90% 88% 91% 90%

Implications
• Use of this model helps close the gaps in the service process

from a customer-centric perspective.
• Concepts such as service blueprinting might be updated

and improved through text mining.
• Addressing gaps in customer-centric service blueprint

could enable organizations to modify service offerings
• How changes in service offerings affect service encounters • How activities and resources are affected.

• The importance of development of text mining patterns could

aid in developing better predictive models

Limitations and Further Research
• The proposed text mining model is domain specific • The proposed model requires work to improve data capture and

accuracy and to be tested for another dataset.
• However, the approach could be tested and adapted to other

domains.
• Further research could investigate how information gathers from text

mining can be integrated in company information systems

Similar Documents

Free Essay

Text Mining

...2013 Submitted To: Prof. Raleigh 06/07/2013 Text Mining Submitted By: Roshan Bhattachan What challenges does the increase in unstructured data present for businesses? Text mining is the discovery of pattern and relationships from large set of unstructured data-the kind of data we generate in emails, phone conversation, blog posting, online customer surveys, and tweets (Laudon & Laudon, 2012). These unstructured data contains lots of useful information, and businesses can use this information to make a better decision making. The challenges for today businesses are how they can make best use of this unstructured information. It’s not a piece of cake to get information out easily because there are millions of information over the internet, and the success of businesses lies in how effectively and efficiently they can process and analyze this information , and use it to make better decision making. It’s a complex and rigorous tasks, and needs people time and money to take out best of information from this unstructured data. How does text-mining improve decision making? Text mining tools are now available to help businesses analyze unstructured data. These tools are able to extract key elements from large unstructured data sets, discover patterns and relationship, and summarize the information. For example: JetBlue in 2007 experienced a number of customer discontent which resulted in large number flight cancelation. It received around 15000 emails per day, and...

Words: 758 - Pages: 4

Free Essay

What Can Business Learn from Text Mining

...Chapter 6 Case I  Interactive Session : Technology WHAT CAN BUSINESSES LEARN FROM TEXT MINING 1. What challenges does the increase in unstructured data present for businesses? Text mining enables many companies to respond to their customers satisfaction surveys, and web mining enables many web search engines to facilitate collecting data that people need to be more profitable. Now, a huge amount of unstructured data is distributed by these systems. A manager is able to use this system and make an accurate decision for unprecedented cases. information Business intelligence tools deal primarily with data that have been structured in databases and files. However, unstructured data, mostly the kind of data we generate in e-mails, phone conversations, blog postings, online customer surveys, and tweets are all valuable for finding patterns and trends that will help employees make better business decisions.  Text mining tools are now available to help businesses analyze these data. These tools are able to extract key elements from large unstructured data sets, discover patterns and relationships, and summarize the information. Businesses might turn to text mining to analyze transcripts of calls to customer service centers to identify major service and repair issues. 2. How does text-mining improve decision-making? Text mining system enables airlines to rapidly extract customer sentiments, preferences, and requests for example, when the airlines suffered from unprecedented...

Words: 532 - Pages: 3

Premium Essay

Text Mining Research Paper

...Text mining is the process of extracting interesting and non-trivial knowledge or information from unstructured text data. Text mining is the multidisciplinary field which draws on data mining, machine learning, information retrieval, computational linguistics and statistics. This research paper discussed about one of the text mining preprocessing techniques. The initial process of text mining systems is preprocessing steps. Pre-processing reduces the size of the input text documents significantly. It involves the actions like sentence boundary determination, natural language specific stop-word elimination, tokenization and stemming. This research paper established the comparative analysis of document tokenization tools. I. Introduction Tokenization...

Words: 1209 - Pages: 5

Free Essay

Text Mining for Gold?

...Problem-Solving Case, Ch. 5 Text Mining for Gold? 1. What is the business impact of text mining? What problems does it solve? Text mining has had a large impact on business. Businesses are able to use text mining techniques to better understand their customers. It allows them access to unstructured data that were not available before, such as Facebook statuses, Twitter tweets, blogs, transcripts from call centers, e-mails, and phone calls. Text mining allows businesses to analyze that information for better decision making and it allows them to consolidate that information at lower costs since the cost of text mining programs is much less than the cost of paying hundreds of people to go through the information manually. It allows businesses to determine their weaker areas of customer service and begin improvements with their customer relations. 2. How does text mining improve operational efficiency and decision making? Text mining improves operational efficiency by use of software programs that analyze the available data and consolidate it. It removes the possibility of human error and allows businesses to save money in wages by reducing the number of employees necessary to manually analyze the information. Text mining improves decision making by allowing businesses access to information that was not available before. For example, according to the textbook, Kia was able to analyze the affect of its Super Bowl commercial by using text mining techniques to determine...

Words: 538 - Pages: 3

Free Essay

Texting Mining for Gold

...Text Mining For Gold 1) What is the business impact of text mining? What problems does it solve? Text mining is the discovery of patterns and relationships from large sets of unstructured data; such as text files, emails, memos, call center transcripts, survey responses, legal cases, patent descriptions, and service reports. Text mining and text mining tools help businesses analyze this data (Laudon 164). The tools are able to extract the key elements from large unstructured data sets, discover patterns and relationships and summarize the information. Businesses use these tools to analyze transcripts of calls to customer service centers to identify major service and repair issues. The problems that are solved with text mining is; it shortens the time to accurately find data. By converting unstructured text into structure output, text mining results can feed into further analytics or be combined with the results of other data analyses. By doing so it enables delivery of comprehensive, high quality text mining results as part of systematic and reproducible workflows. 2) How does text mining improve operational efficiency and decision making? Text mining improves efficiency and decision making by providing the tools such as software so that companies can choose what data they want to focus on. Text mining software is starting to get popular and software companies are developing software to accommodate business needs. Example, the Law Firm DLA Piper discussed in...

Words: 815 - Pages: 4

Free Essay

Social Media White Paper

...Media Data: Network Analytics meets Text Mining Killian Thiel Tobias Kötter Dr. Michael Berthold Dr. Rosaria Silipo Phil Winters Killian.Thiel@uni-konstanz.de Tobias.koetter@uni-konstanz.de Michael.Berthold@uni-konstanz.de Rosaria.Silipo@KNIME.com Phil.Winters@KNIME.com Copyright © 2012 by KNIME.com AG all rights reserved Revision: 120403F page 1 Table of Contents Creating Usable Customer Intelligence from Social Media Data: Network Analytics meets Text Mining............................................................................................................................................ 1 Summary: “Water water everywhere and not a drop to drink” ............................................................ 3 Social Media Channel-Reporting Tools. .................................................................................................. 3 Social Media Scorecards .......................................................................................................................... 4 Predictive Analytic Techniques ............................................................................................................... 4 The Case Study: A Major European Telco. ............................................................................................. 5 Public Social Media Data: Slashdot ......................................................................................................... 6 Text Mining the Slashdot Data .................

Words: 5930 - Pages: 24

Free Essay

Hgchlg

...I am extremely grateful to him for providing me the necessary links and material to start the project and understand the concept of Twitter Analysis using R. In this project “Twitter Analysis using R” , I have performed the Sentiment Analysis and Text Mining techniques on “#Kejriwal “. This project is done in RStudio which uses the libraries of R programming languages. I am really grateful to the resourceful articles and websites of R-project which helped me in understanding the tool as well as the topic. Also, I would like to extend my sincere regards to the support team of Edureka for their constant and timely support. Table of Contents Introduction 4 Limitations 4 Tools and Packages used 5 Twitter Analysis: 6 Creating a Twitter Application 6 Working on RStudio- Building the corpus 8 Saving Tweets 11 Sentiment Function 12 Scoring tweets and adding column 13 Import the csv file 14 Visualizing the tweets 15 Analysis & Conclusion 16 Text Analysis 17 Final code for Twitter Analysis 19 Final code for Text Mining 20 References 21 Introductions Twitter is an amazing micro blogging tool and an extraordinary communication medium. In addition, twitter can also be an amazing open mine for text and social web analyses. Among the different softwares that can be used to analyze twitter, R offers a wide variety of...

Words: 2107 - Pages: 9

Free Essay

Life

...Opinion Mining Using Econometrics: A Case Study on Reputation Systems Anindya Ghose Panagiotis G. Ipeirotis Arun Sundararajan Department of Information, Operations, and Management Sciences Leonard N. Stern School of Business, New York University {aghose,panos,arun}@stern.nyu.edu Abstract Deriving the polarity and strength of opinions is an important research topic, attracting significant attention over the last few years. In this work, to measure the strength and polarity of an opinion, we consider the economic context in which the opinion is evaluated, instead of using human annotators or linguistic resources. We rely on the fact that text in on-line systems influences the behavior of humans and this effect can be observed using some easy-to-measure economic variables, such as revenues or product prices. By reversing the logic, we infer the semantic orientation and strength of an opinion by tracing the changes in the associated economic variable. In effect, we use econometrics to identify the “economic value of text” and assign a “dollar value” to each opinion phrase, measuring sentiment effectively and without the need for manual labeling. We argue that by interpreting opinions using econometrics, we have the first objective, quantifiable, and contextsensitive evaluation of opinions. We make the discussion concrete by presenting results on the reputation system of Amazon.com. We show that user feedback affects the pricing power of merchants and by measuring their pricing...

Words: 6122 - Pages: 25

Free Essay

Analytics Text Mining

...Task A: Text Clustering - 2 Clusters After running the Text Cluster, the following observations were obtained: Table 1. Cluster Summary Cluster Weight Frequency RMSSTD Cluster Description 1 0.8 2248 0.124345 +action +good +plot characters effects movies pretty +movie real +year first +old +few +end films +character +feel +watch +cast +director 2 0.2 551 0.094437 +battle +history +man +stone alexander angelina anthony battles colin farrell historical hopkins hours jolie men oliver scenes stone troy +life Table 2. Cluster-Specific Means Cluster Rat_10scl (mean) Useful (mean) RevLen_Words (mean) 1 6.121 0.388 241.981 2 5.461 0.413 277.301 Table 3. Cluster-Specific Genre Distribution Cluster thriller romance action drama comedy animation Sum 1 11.65% 5.43% 40.39% 25.71% 15.97% 0.93% 100% 2 0.36% 0.36% 13.07% 86.21% 0% 0% 100% Description of the clusters: Cluster 1: This cluster has larger number of observations under it which is 80% of total reviews with a frequency, that is, number of reviews of 2248. Total number of reviews processed is 2799. Even though this cluster is larger, from the value of RMSSTD of 0.124 which is higher than that of Cluster 2, it shows that this cluster is more heterogeneous. That is, the reviews are more varied and inconsistent. Overall from the list of terms displayed under the ‘Descriptive Terms’, we see quite a different variety of terms. Terms like ‘plot’, ‘characters’, ‘cast’, ‘director’, ‘watch’, etc, shows that this cluster...

Words: 745 - Pages: 3

Free Essay

Als Icebucketchallenge

...DATA PREMIER LEAGUE Case 2: ALS IceBucketChallenge Objective: Sentiment analysis of twitter tweets and facebook posts during the Ice Bucket Challenge ALS Ice bucket challenge is an activity which involves dumping of ice water on one’s head to promote awareness of the disease ALS as an alternative for donation. It went on viral during July and august 2014. Challenge encourages nomination of other kith and kin’s to do the same within 24 hrs. Methodology: Data Preprocessing: From the given data all redundancies were cleaned up. By using vector source in Corpus, we cleared punctuation marks, numbers, converting all the words into a single case (as it is casesensitive), removing stop words which do not make sense in the sentence, stripping out whitespace and http links were removed. Clearing all this unnecessary data, we get the content which makes actual sentiment overall in each post/tweet. Data Analysis: The overall sentimental score was developed using an algorithm which contains 7 liker scale using R tool by considering the standard Positive and negative words. Categorical analysis was performed using excel based API developed on the NLP algorithm used by Semantria to get individual categorical analysis as to how the emotions and trend was The statements were split into words and un-listed the results in a list of words. Matched these un-listed words to the Positive master list and this returns the indices of all the matched words. The attempt made here is...

Words: 552 - Pages: 3

Free Essay

Text Analytics

...Selection of the topic- Text Analytics Title- Using text analytics to improve the hospitality experience of customers. Key Words- Text analytics, content categorization, sentiment analysis, Abstract- With advance text analytics solutions, the hotels and hospitality providers can analyze conversations on the social media and online public forums to extract valuable business insights and using the same to improve their customer’s experiences into their hotels and with their services. Introduction- Today’s travelers are vocal and willing to share their experiences with hotel and travel providers; they’re more apt to share their experiences online with others through means of social media like- facebook & twitter, in online review sites such as tripadvisor.com etc. From check-in process to the quality of services, their feedbacks provide valuable insights that hospitality providers can improve the guest experience with their brands, better target customers with offers and differentiate ‘emselves from the competitors in terms of products and services. Collecting quantitative responses from the guests through surveys was the sole feedback method used by hotels and travel service providers. Of late, the trend has changed. These days, these providers recognize the value of collecting feedback through social media and other online sites. They even encourage open-ended comments in their surveys these days. With thousands of reviews generated each day, compiling and interpreting...

Words: 890 - Pages: 4

Free Essay

Wendy's International Case Study

..."Wendy's International Relies on Text Mining for CEM," and answer the. Select one side of the argument as described and provide convincing points either in favor or against the proposal that an investment in text message collection and mining should be made even if no clear positive ROI (return on investment) from better execution can be determined in advance. A healthy customer relationship plays a crucial part in the success of a business. In today's competitive marketplace, every organization wants to know whether its customers are satisfied with the company services or not and their views about the products and services. These all things can be done with a customer survey. Companies can get many benefits by surveying their customers. It is really an inexpensive way to get customer feedback which can help the company to improve customer retention, and customers' suggestion or their creative ideas can help to improve company's product or may help to launch a new product. A company can survey its customers by several ways including text messaging,web-based feedback forms, social media, e-mail messages, call center notes and receipt-based surveys. Nowadays scenario has been changed. People are always on move, you are not able to see them sitting all the time in front of the computer. But most of all the people keep their mobile with them 24 hours a day. So when the company sends its customers survey questions through text message, the text message is arrived instantaneously...

Words: 1055 - Pages: 5

Free Essay

Student

...HP and Text Mining What is the pratical application of text mining: The practical application of text mining really is the combination of structured and unstructured data. Text mining applications pull data from sources such as word documents and emails in the form of texts, filters the data, and then translates it into a format the can be analyzed and recorded. Without text mining, written texts and other unstructured data would really become worthless data sources. According to studies done on BI and data mining, businesses and other BI clients are looking more and more to unstructured data as a primary data source. Probably the most pratcial application of text mining would have to be marketing. How do you think text mining techniques could be used in other businesses: There is almost a limitless amount of applications for text mining in other businesses. The most obvious use of text mining for other businesses would be to analyze written customer reviews and/or comments. Essentially, Text Mining can be used anywhere where there is a direct and free form line of communication between an entity and its actors. In the past, only a human was able to read, translate, record, and respond to these lines of communications. Text mining allows these processes to be completed without any human assistance. This means that new divisions and processes within a company could become automated such as responses to customer inquiries. What were HP’s challenges in...

Words: 433 - Pages: 2

Premium Essay

Brands During The Gold Rush

...One of the few examples that Brands goes into great detail in is the account of John C. Fremont. Fremont is one of the more interesting figures in the text; he was once an officer who helped secure the current state of California from the Mexicans, but then he turned his attention to turning a profit of his own from the gold rush. Brands goes into vivid detail about each individual and their struggles along their travels across the United States. Brands gives an excellent account about the ship bearing travelers who came to California through either Panama or around South America. He also covers the shipping business and the effect the gold rush had upon it. Although Brands did an excellent job in the detailing the expeditions to California he spent too much time on the Argonauts, it almost felt more of a biography instead of an account of the gold...

Words: 1153 - Pages: 5

Premium Essay

Chilean Mine Workers

...Over 30 workers were trapped after a Chilean copper mine collapsed in 2010. According to "Chile Mining Accident (2010)" (2013), On Aug. 5, 2010, a gold and copper mine near the northern city of Copiapó, Chile caved in, trapping 33 miners in a chamber about 2,300 feet below the surface. For 17 days, there was no word on their fate. As the days passed, Chileans grew increasingly skeptical that any of the miners had survived — let alone all of them. But when a small bore hole reached the miners’ refuge, they sent up a message telling rescuers they were still alive (para. Background). The families of these workers and the news release to society and the other employees of the company would have been told in different communication styles. How we communicate to people will fluctuate depending on the roles of the individual or group and the act that has occurred or will occur. PARAGRAPH III: What would be the potential needs of the families of the miners in receiving a message about this incident? One communication should be directed to the families of the trapped miners PARAGRAPH IV: What would be the potential needs of the company’s employees when receiving a message about this incident? One communication should be directed to the other as an internal news release to employees in the company. Identify the most appropriate channel—face-to-face, e-mail, video, memo, text messages, phone calls, and so on. I would probably communicate with the company’s employees...

Words: 424 - Pages: 2