Kinds of Texts Would Accountants Needs to Read
Textual analysis, also known equally content analysis, involves examining the content, structure, and functions of messages contained in unstructured (or text) data by applying linguistic theory.
Driven by the rapid growth in computer processing capability and in both internal and external unstructured data, textual assay is now used in accounting and auditing settings. It allows accountants to identify key terms in lease agreements and to track customer contracts for revenue recognition purposes, auditors to review periodical entry descriptions, and investors to compare direction discussion and assay (MD&A) between companies.
Textual analysis is especially important today due to the increased emphasis in accounting on unstructured data, which includes not only documents merely too emails, text messages, logs and notifications, video and audio files, and notwithstanding images. Textual analysis allows accountants and auditors to analyze this data and use it to drive decision making. Further, textual analysis provides accountants with additional knowledge beyond quantitative data, including insight into complex models of human thought and language use.
Nothing's perfect, nonetheless. Textual analysis has some drawbacks, as it tin be time-consuming and users need to exist careful non to jump to conclusions as well rapidly with their interpretations. In addition, its iterative process may exist frustrating at times, specially for inexperienced users. There may be software issues also.
KEY CONCEPTS OF TEXTUAL ANALYSIS
Textual analysis is an iterative process involving several concepts. Earlier getting started, however, accountants and auditors should be familiar with the following textual analysis concepts: give-and-take count, concordance, discussion deject, word search, discussion copse, collocation, fog index/readability, and sentiment analysis (tone). Let's take a closer look at each of these.
Discussion count:Give-and-take count is a method that totals the number of words in a certificate or a sentence. Near sentences in accounting documents include between 20 and 25 words. Sentences longer than this will therefore lower the document's readability score. Worse, some analysts may suspect that the level of verbosity in sure documents represents the company's try to hide something.
Discussion count can as well tally how many times a specific give-and-take appears within the certificate. For example, if Company A uses the discussion "loss" 40 times in its annual written report, and a competitor, Company B, uses it 15 times, someone may question whether Company A is worse off than Company B.
Concordance:Related to word count, a concordance is a listing of the frequency of all words in a document along with the immediate words surrounding each word. Thus, a concordance provides context for the word occurrences, which enables greater insight into how a word is used in the certificate. Textual analysis software can besides count the number of pages, paragraphs, and lines in the text. Most software too displays the number of characters, either including or excluding spaces.
Word cloud:Give-and-take clouds are graphical representations of word frequency. Words that appear more oft in the source text announced bigger and bolder in the word cloud, which tin be used to communicate the virtually salient points or themes in the text. For example, a visitor that makes sporting appurtenances might use a give-and-take deject to analyze customer reviews of running shoes to visually display the specific words used by customers and thereby decide what is most important to them.
Give-and-take search:Given the iterative nature of textual analysis, it may involve multiple word searches. For example, a word count may suggest that the term "risks" is used in the Dr.&A section of an annual written report multiple times. The user may then search this section for each occurrence of "risks" to look for clues regarding the types of risks discussed.
Word trees:Word copse are a visual representation of a set of words, using a branching construction to illustrate relationships betwixt words. Thus, words that are more commonly used within a document are given a "tree," and each "branch" represents words that are associated with the "tree" word. This gives users an thought of the connotation each give-and-take has within the documents.
Word trees can aid users to amend interpret discussion meanings within the document without having to read the entire document. In Figure 1, for case, the main term, "internal control," has multiple phrases or words that appear immediately before or after it in the document. Equally with a word cloud, the bigger and bolder the word or phrase that precedes or follows the master term appears, the more oftentimes that word or phrase is used in the document. A word tree is a visual concordance.
Collocation:Certain words are often ready in close proximity, or collocated, to each other. For instance, consider the terms "fiscal" and "argument." Several textual analysis packages will identify collocated words like this without user intervention. In accounting, identifying common collocated words, such as "long-term debt," "marketable securities," and "fixed asset," is helpful in determining the text'southward meaning.
Fog index/readability:Equally the term implies, fog alphabetize (or readability) measures how difficult text is to understand. The fog index is a linear combination of average sentence length and proportion of circuitous words, with complex words being defined as those with more than 2 syllables. There are 2 standard readability tests: Flesch Reading Ease and Flesch-Kincaid Grade Level. Both tests use the aforementioned cadre word length and sentence length measures, but each examination uses different weighting factors. The results of the two tests correlate inversely—that is, text with a comparatively loftier score on Reading Ease will take a lower score on the Grade Level test.
Contempo accounting research has shown that the fog index isn't a proficient measure of financial argument readability given that many terms used in business texts are complex words that are by and large familiar to investors and analysts. For example, consider common fiscal argument words such as "contingency," "deviations," "preliminary," "probable," and "recalculate." To address this issue, accounting professors Tim Loughran and Beak McDonald suggest that, for business organisation texts, simply using document length or file size is a more efficient and effective proxy for conventional readability indices.
Sentiment assay (tone):Sentiment analysis focuses on the specific tone or emotions expressed in a certificate. In that location are two types of sentiment analysis: One is focused on the polarity of documents (positive, negative, or neutral), the other on more specific emotions (doubt, litigiousness, etc.). Net sentiment assay identifies words in a certificate equally either positive or negative in tone and then calculates a net divergence. The divergence can either be positive (more positive words than negative), negative (more negative words than positive), or neutral (an equal number of positive vs. negative words).
Sentiment analysis focused on the detection of specific emotions in text uses specific word lists (where the words are considered indicative of the emotion of interest) equally filters. The specific give-and-take listing is input to the software tool used for the analysis and is employed to identify the occurrences of the words on the list. If a high number of words in the list announced in the bookkeeping certificate, then the overall tone of the report can be determined based on the sentiment word list that was used. For example, if an uncertainty word list was used and textual analysis indicates that the document examined has a high number of uncertainty words, then the textual assay would advise that the document had an cryptic tone. For financial data, sentiment analysis oft uses the Loughran and McDonald Sentiment Word Listing to identify overall tone of a certificate.
Three Central METHODS
Textual analysis software is driven by several types of methods, the virtually mutual of which are auto learning, natural language processing (NLP), and network assay.
Machine learning:Machine learning uses AI to train computers to wait for patterns that can exist used in bookkeeping. With motorcar learning, the textual assay software checks for word counts, uses discussion trees to connect mutual words, and runs a fog index to get the overall tone of the document. Machine learning is instrumental in the success of textual analysis and can help the accounting field to evolve.
Natural linguistic communication processing:NLP builds on machine learning and pulls meaning from unstructured data. Information technology's often used to translate accounting documents from i language to another. NLP can likewise summarize documents then that investors tin read them more than quickly and easily.
Network analysis:Network analysis finds connections between dissimilar types of information. Specifically with textual assay, this method is implemented with discussion trees to accurately group different texts into what's referred to as "notes." The notes are included in images to demonstrate how they're continued to i another based on words they have in common. Figure 2 shows an example of how network analysis tin can help to improve textual analysis past making it easier to scrutinize text. Within the accounting field, network analysis tin can be used to connect different types of visitor reports (10-Ks, 10-Qs, annual reports, and and then on) to one another based on the keywords in each certificate.
Bookkeeping AND AUDITING APPLICATIONS
Accountants and auditors use textual analysis in several areas, and its employ is expected to increase significantly in the coming years. With that in mind, here are some of the areas in which textual analysis tin provide a value-added approach to routine business and compliance functions.
Contract assay:KPMG manages client contracts using its proprietary Cognitive Contract Direction system. Contract data is loaded into the system, which analyzes each contract to place cardinal terms to save KPMG time and coin. Similarly, Deloitte uses a proprietary software called dTrax, which blends AI and machine learning to examine and manage contract portfolios. This process saves Deloitte pregnant hours and costs as it evaluates contract pricing, service offerings, and staffing support. (For more than, come across "Real-World Uses of Textual Assay" at the end of the commodity.)
Lease accounting:Fiscal Accounting Standards Lath (FASB) Accounting Standards Codified (ASC) Topic 842, Leases, requires many companies to record an asset and liability on the balance sheet for most leases. To avert misstating the residuum sheet, companies demand to ensure that they have identified and reviewed contracts for all embedded leases. Many companies now apply textual assay to handle these tasks.
Revenue recognition:The new revenue recognition standard, ASC 606, Revenue from Contracts with Customers, requires companies to examine customer contracts. Many large companies and their external auditors use textual analysis to identify unique contract features, such as contract length, payment terms, risk, and timing, besides as corporeality of future cash flows, payment obligations, and payment dates.
General ledger periodical entries:Auditors may use textual analysis to review full general ledger journal entries to look for high-hazard entries. For instance, EY Helix has analyzed more than 580 billion lines of journal entry descriptions in the past 12 months. These journal entry descriptions may identify red flag transactions that require further investigation, such as transmission entries made belatedly in the fiscal period.
Footnote disclosures:Auditors often rely on textual analysis to examine client footnote disclosures. For example, ane large audit firm has used textual analysis to identify key components of publicly traded visitor footnotes by industry. The house compares the footnote disclosures of each client to the information in its disclosure database, looking for discrepancies that may warrant further investigation.
Management discussion and assay:MD&A provides investors with information about a company's past functioning, futurity goals, and new projects. For investors and analysts evaluating multiple companies, textual assay can help monitor and organize this data.
Monitoring social media sentiment: Today, organizations need to continually monitor their social media presence, as i poorly timed negative social media incident can significantly affect an system'south reputation and even have fiscal implications. As a result, several organizations are turning to textual analysis to monitor social media and identify potentially harmful posts.
Privacy compliance:Recently, organizations accept spent significant time complying with data privacy regulations, including the European Union's General Information Protection Regulation and the California Consumer Privacy Act. Textual analysis can assist organizations by identifying all impacted data for review to ensure compliance with privacy regulations.
Video recordings of interviews:During the COVID-19 pandemic, auditors replaced face-to-face inquiries with video conferences. In general, the content of video briefing interviews can exist recorded and transcribed easier than a face-to-face inquiry. Using textual analysis software, auditors can examine these transcripts for indicators of potential fraud, phrases such as "write-off" or "failed investment."
TEXTUAL ANALYSIS SOFTWARE
Unlike graphical representation software, where Tableau and Power BI are now widely used, most textual assay software remains proprietary. Organizations that we spoke with indicated that developing textual analysis software internally helped them obtain a competitive advantage in this fast-growing field.
But your company doesn't necessarily have to create its ain software to benefit from textual analysis. Here are some details on two gratuitous textual assay software packages: AntConc and RapidMiner.
AntConc specializes in analyzing text to notice different patterns. Equally with whatsoever textual analytics programme, users start past converting all documents into text files and uploading the files to the AntConc software. I claiming in using AntConc is that words need to exist typed in ane by one instead of loading a list of words. For example, the 2017 annual reports of Sears and Target can be compared by using the Loughran and McDonald Sentiment Word List for the words pertaining to "dubiety." Consider the word "risks," for example. The 2017 Sears almanac written report used the word "risks" 24 times, while the Target annual report included it but 14 times. To give the reader some context, the analysis too shows the sentences in which the word "risks" appears (see Figure iii).
Nosotros too ran an analysis for the discussion "uncertainties." In the Sears almanac study, "uncertainties" is used 7 times, whereas the Target annual study included it only three times. While this needs further investigation, the AntConc results therefore propose that Sears had a greater number of uncertainty words within its 2017 annual report than Target. This could signal a higher potential of fraud and would thus crave further investigation.
Compared with AntConc, RapidMiner is more avant-garde, as it includes both machine learning and predictive analytics and requires a textual analysis extension in social club to perform textual analysis, including the utilize of the Loughran and McDonald Uncertainty Word Listing for the dubiety sentiment assay.
Unlike AntConc, RapidMiner allows users to upload word lists rather than single words. Nosotros used RapidMiner to analyze the 2017 Sears and Target accounting documents, using the third-quarter 10-Q (see Tabular array 1). Sears had many more incertitude words when compared to Target. The highest number of repetitive uncertainty words was 74 for the word "approximately" in the Sears x-Q, while the highest number in the Target 10-Q was nine for "believe."
While AntConc and RapidMiner both identified differences between Sears and Target, each has its own pros and cons. The AntConc software is easier to navigate and doesn't require users to download a textual analysis extension. Farther, AntConc provides a sentence preview so users can see how each word is used inside the bookkeeping document.
Although more hard to navigate, RapidMiner offers a much more than all-encompassing search. And, as mentioned before, it also allows users to search by multiple words by loading in a word list vs. one word at a fourth dimension with AntConc. Both systems, yet, have similar outputs.
WHAT Information technology Means TO You lot
With technology now providing the means to clarify unstructured data more rapidly and efficiently, condign practiced with textual assay is an important skill for accountants and auditors to master. Every bit the volume of unstructured data continues to grow, textual analysis tin can enable your arrangement to glean many interesting and useful insights to reduce run a risk, ameliorate performance, and, in the process, remain a step alee of the competition.
Just put, if you're a management accountant or financial professional with a line to the C-suite, now is the time to lay the groundwork for an "all-in" approach to this value-added engineering science.
Real-World Uses of Textual Assay
Deloitte
Deloitte's dTrax, which uses AI and machine learning to examine and manage contract portfolios, can be customized to fit clients' needs. Partnering with OpenText technologies, Deloitte is developing data solutions for the utilities, oil and gas, and food service industries.
EY
EY developed Forensic Data Analytics for clients' compliance with the Eu'south General Data Protection Regulation. EY'south goal is to identify data patterns from multiple data sources that demand closer attention for compliance monitoring. EY also adult EY Helix, a global audit analytics tool, to analyze journal entry descriptions.
KPMG
KPMG adult its Cognitive Contract Management system for clients to analyze contracts. KPMG says the system will assistance organizations address commercial leakage, clause compliance, and contract pricing comparisons, also as internal audit, legal section, and supplier operation problems. KPMG also advertises an Intelligent Underwriting Engine that uses textual analysis to identify underwriting risks through contract review.
PwC
PwC claims to take fabricated a significant investment in natural language processing for supply chain direction applications, to increase transparency, improve planning, and enhance logistics flows.
BDO
BDO uses textual assay to examine big amounts of unstructured client information in order to assistance clients in complying with the California Consumer Privacy Act and other data privacy and protection principles. The visitor has as well partnered with Brainspace to develop textual analytics applications, including those that will aid in fraud investigations, support litigation, due diligence, and gamble assessments.
Crowe LLP
Crowe uses textual analysis for insurance claims clients. The company says its application examines interview notes, adjuster case commentaries, medical reports, and similar text-based formats. Crowe recently partnered with Overnice Actimize to develop applications that can identify financial service manufacture criminal offense.
Grant Thornton
Grant Thornton offers Ephesoft Smart Capture solutions to assistance clients evaluate unstructured data specifically related to dorsum-end processes, such as invoicing, accounts payable, and contract management. Grant Thornton has adult cerebral automation to leverage structured, semi-structured, and unstructured data for taxation applications. The company claims this technology recognizes voice, images, fuzzy logic, and other unstructured taxation information.
RSM
RSM uses textual analysis in forensic data analytics to combine information from multiple sources. The company claims its awarding volition help investigators quickly identify big-movie discrepancies and connect the dots in fraud cases.
Diane Janvrin, Ph.D., CMA, is the William 50. Varner Professor of Accounting in the Debbie and Jerry Ivy College of Business at Iowa State Academy. She's as well an IMA fellow member. Y'all can reach Diane at (515) 294-9450 or djanvrin@iastate.edu.
Ingrid Fisher, Ph.D., CPA, CFE, is an acquaintance professor of bookkeeping in the School of Business at the University at Albany-SUNY. You can reach her at (518) 956-8365 or ifisher@albany.edu.
You may also like
Source: https://sfmagazine.com/post-entry/june-2021-textual-analysis-for-accountants/
0 Response to "Kinds of Texts Would Accountants Needs to Read"
Post a Comment