| Course | DBA-8060 Empirical Entrepreneurship Data, Technology, and Business Intelligence |
|---|---|
| Module | Module 5 |
| Paper type | Module 5 written assignment: text, web and social media analytics |
| Length | About 523 words, 4 pages |
| Format | APA 7 student paper |
| School | Thomas Edison State University |
| Program | Doctor of Business Administration |
| Updated | October 2026 |
Free sample paper for DBA 8060 Module 5
The Lead Times Are in the Inbox: Text and Social Media Analytics for DAKOKOO Distribution
Student Name
Doctor of Business Administration, Thomas Edison State University
DBA-8060: Empirical Entrepreneurship: Data, Technology, and Business Intelligence
Mentor Name
Month Day, Year
The Lead Times Are in the Inbox: Text and Social Media Analytics for DAKOKOO Distribution
Introduction
Earlier analysis showed that 59 percent of DAKOKOO's import orders lack a recorded receipt date, which blocks any study of lead times. The dates are not lost; they sit in emails from suppliers, freight forwarders and carriers. Text analytics can recover them, and social media can add a signal the firm does not now see: shoppers reporting empty shelves.
Text Mining the Inbox
Sharda et al. (2018) describe text mining as the process of turning unstructured text into structured data that can be analyzed, through steps of collecting documents, building a term-by-document representation and extracting patterns. Chen et al. (2012) identify text analytics as one of the main frontiers of business intelligence because much organizational knowledge is held in text.
The process has four steps. First, collect twelve months of messages from the purchasing mailbox, about 186,000 emails. Second, classify each message by type: shipment confirmation, delay notice, arrival notice or other. I would label 3,000 emails by hand and train a classifier on them, testing it on a held-out set of 500. Third, extract entities from the relevant messages: purchase order numbers, which follow a fixed pattern, and dates, ports and vessel names. Fourth, join the extracted events to purchase orders in the warehouse, so each order gains a shipped date and an arrival date.
Delay notices carry a further benefit: their stated reasons, such as port congestion or a missed booking, can be grouped to show which causes recur by supplier.
| Message type | Share of sample | Fields extracted | Use |
|---|---|---|---|
| Shipment confirmation | 21 percent | PO number, ship date, vessel | Start of transit |
| Delay notice | 9 percent | PO number, new date, reason | Variability and causes |
| Arrival notice | 17 percent | PO number, port, arrival date | Lead time end point |
| Other | 53 percent | None | Excluded |
Social Media as an Early Signal
Shoppers post photographs of empty shelves and complaints about missing products on public social media. Kietzmann et al. (2011) describe social media through functional building blocks such as conversations, sharing and reputation, and they argue that firms must decide which blocks matter to them before acting. For DAKOKOO the relevant block is conversation: public posts that name a product and a store could warn of shortages before store systems do.
Sentiment analysis would be less useful here. Pang and Lee (2008) review methods for classifying opinions and show that they struggle with context, sarcasm and domain shift, so a model trained on product reviews may misread posts about availability. Counting mentions of out-of-stock terms by product and region is simpler and easier to validate.
Ethical Boundaries
Only public posts would be used, analyzed in aggregate by product and region, with no collection of user identities. Supplier emails are business records, but they may contain personal names and phone numbers, which the extraction step should drop.
Conclusion
Text analytics can fill DAKOKOO's largest data gap from records it already holds, while social posts offer a modest early signal if used with care. The inbox should be mined first because it repairs the data on which every later model depends.
References
Chen, H., Chiang, R. H. L., & Storey, V. C. (2012). Business intelligence and analytics: From big data to big impact. MIS Quarterly, 36(4), 1165-1188. https://doi.org/10.2307/41703503
Kietzmann, J. H., Hermkens, K., McCarthy, I. P., & Silvestre, B. S. (2011). Social media? Get serious! Understanding the functional building blocks of social media. Business Horizons, 54(3), 241-251. https://doi.org/10.1016/j.bushor.2011.01.005
Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2), 1-135. https://doi.org/10.1561/1500000011
Sharda, R., Delen, D., & Turban, E. (2018). Business intelligence, analytics, and data science: A managerial perspective (4th ed.). Pearson.
DBA 8060 Module 5 instructions, in plain terms
Words as data are the subject of the fifth DBA-8060 module, and one of the five written assignments is matched to it here because the syllabus gives no schedule for them. Expect to identify text an organization holds or can observe, design a process that turns it into structured data, judge which methods suit the task and set ethical limits on the data used. Sharda, Delen and Turban's chapter on text and social analytics covers the process and methods, and journal articles in the module extend it. Concrete numbers, such as message volumes and labeled samples, make a design credible, and explaining where a popular method such as sentiment analysis does not fit shows judgment.
How this DBA 8060 Module 5 example is built
The paper starts from a gap found in Module 2: most import orders lack receipt dates. It locates those dates in the purchasing mailbox and designs a four-step text mining process: collect, classify, extract and join. A table reports message types from a labeled sample with the fields each yields. A paragraph notes that delay notices also reveal causes. The social media section uses Kietzmann's building blocks to pick conversation as the relevant function and counts out-of-stock mentions rather than relying on sentiment, which Pang and Lee show struggles with context. An ethics section limits social data to public, aggregate use and strips personal details from emails.
Where the marks sit in the DBA 8060 Module 5 rubric
Mentors grade written assignments in DBA-8060 on accurate use of analytics concepts, research support, application and critical thinking, with APA style throughout. In this module, credit goes to designs that show each step of text processing rather than naming software. Matching methods to the task, and rejecting a popular one where it does not fit, shows judgment. A labeled sample and a test set show awareness of how text classifiers are validated. Addressing privacy and ethics specifically, with rules the organization could follow, meets the managerial perspective the course takes. Clear links to earlier analysis make the assignment part of a coherent program. Mentors also credit a design that names its own failure points, such as emails in other languages.
DBA 8060 Module 5 help from the desk
Assignments in this module often describe text mining and social media analytics in general terms, recommend sentiment analysis for every problem or ignore ethics. Others propose monitoring social media without saying what decision the data would support. Find text your organization already holds that answers a real question, describe each processing step and say how you would test the results. Choose methods for the task, not for their popularity, and set clear limits on personal data. Connect the output to a model or decision you have already described. A free first draft of your DBA-8060 Module 5 assignment can be prepared on your own organization's text sources. Report what share of the labeled sample the classifier got right before any wider rollout.
Write yours, or have the desk draft it
This paper is an original model document written by our desk, not a submitted student paper and not an official Thomas Edison State University document. Read it for the moves, then write your own to the instructions in your classroom. If you want one built to your exact prompt and rubric, the first custom sample is free and arrives in 24 to 48 hours.
More DBA 8060 and Doctor of Business Administration sample papers
- DBA 8060 Module 1: Written Assignment: Big Data as an Entrepreneurial Opportunity at a Retail Distributor
- DBA 8060 Module 2: Written Assignment: Lead-Time Data, a Regression and Two Charts for DAKOKOO
- DBA 8060 Module 3: Discussion: A Star Schema and a Scorecard for DAKOKOO's Retail Contracts
- DBA 8060 Module 4: Written Assignment: Predicting Stockout Risk With a Classification Tree
- DBA 8060 Module 6: Written Assignment: Optimizing Safety Stock and Simulating Expedite Costs
- DBA 8060 Module 7: Discussion: Batch, Stream or Managed Cloud? Choosing DAKOKOO's Big Data Tools
- DBA 8060 Module 8: Final Project: A White Paper on Implementing Big Data at DAKOKOO Distribution
- OML 8030 Module 2: Readiness and Resistance Seminar Paper: How Employees Come to Support Change
- DBA 8020 Module 2: Written Assignment: Estimating Demand and Elasticity for a Refill Subscription
- DBA 8030 Module 1: Discussion: From Great Men to Situations in a Bank's Leadership History
- DBA 8080 Module 3: Written Assignment: Passing On What Retiring Lenders Know
DBA 8060 Module 5 questions, answered
Where can I find a free DBA 8060 Module 5 sample paper?
The paper above designs text and social media analytics to recover DAKOKOO Distribution's missing lead-time data.
What is text mining?
Turning unstructured text, such as emails or documents, into structured data that can be counted, classified and analyzed.
What are the limits of sentiment analysis?
It struggles with sarcasm, context and shifts between domains, so models trained on one kind of text may misread another.
What are the building blocks of social media?
Seven blocks in Kietzmann's honeycomb: who people are, what they say, what they share, whether they are online, whom they know, how they are regarded and which groups they join.
How do you validate a text classifier?
Label a sample by hand, train on part of it and measure performance on a held-out set the model has not seen.