Patent Application
20140280168
If businesses are able to obtain an accurate assessment about the interests held by consumers, then the businesses can act upon that knowledge to more effectively market products and services to those consumers. For example, accurate information about topics and subjects of interest to consumers can be to create sales leads or more targeted advertising to the consumers.
One possible way to obtain this information is to ask consumers to fill out surveys and to then use the survey responses to target the consumers having interests in particular products and services.
However, there are numerous known problems with this approach. First, many surveys tend to have low response rates. In addition, consumers may not necessarily respond honestly or comprehensively to the survey questions, causing concerns about the accuracy of the survey results. Also, surveys are often targeted at certain demographic groups of consumers, which may erroneously pre-filter other consumers that should be included within the target audience for the business.
Therefore, there is a need for an improved approach to perform analysis of possible consumers for businesses and enterprises.
Embodiments of the present invention provide an improved system, method, and computer program product for analyzing interests of consumers. Semantic analysis is performed on writings by authors on social media sites. The results of the semantic analysis provide a profile of the authors. These author profiles can be used to identify and correlate topical interests by consumers. An enterprise or business can more effectively market to the consumers based upon this knowledge of the consumers' interests.
Other additional objects, features, and advantages of the invention are described in the detailed description, figures, and claims.
Given the widespread availability and usage of the internet by consumers, many businesses have become interested in being able to effectively monitor the content and commentary provided by such consumers. Interactive websites such as social networks and blogs provide a wealth of useful information that can be advantageously used by a business. Therefore, it would be very useful to provide an effective mechanism to allow businesses and enterprise business applications to interact with and take action upon data that originate from online sources of social data and commentary.
The present disclosure is directed to an approach for allowing a business entity to access and integrate with social media data. The invention is capable of accessing data across multiple types of internet-based sources of social data and commentary and to perform semantic analysis upon that data. Semantic analysis is performed on writings by authors on social media sites. The results of the semantic analysis provide a profile of the authors. These author profiles can be used to identify and correlate topical interests by consumers. An enterprise or business can more effectively market to the consumers based upon this knowledge of the consumers' interests.
The author profiling tool 106 provides a framework for analyzing writings generated by authors on social media sites. The author profiling tool 106 receives data from one or more online social data sources. Such social data sources include, for example, websites such as a social network, blog or web feed (e.g., Facebook, Twitter, Blogger, and RSS). The content may include one or more comments (e.g., Facebook comment, comment to a blog post, reply to a previous comment) or uploaded postings (e.g., images and associated metadata, text, rich media, URLs) at one or more sources. The social data/content may therefore comprise a variety of forms and/or types.
Semantic analysis, classification, and filtering are performed upon the author writings. Essentially, the writings of the authors are reviewed to identify the topics and subjects of the author's works. This type of analysis can then be performed for multiple authors, where authors having similar analysis vectors are grouped together. Actionable data can then be identified based upon the analysis results.
According to some embodiments, integration is provided between the author profiling tool 106 and an enterprise application 104. The enterprise application 104 comprises any business-related application that provides visibility and control over various aspects of a business. Such enterprise/business applications can include, without limitation, customer relations management (“CRM”) applications, enterprise resource planning (“ERP”) applications, supply chain management applications, and other applications dealing with various finance, accounting, manufacturing, human resources, and/or distribution functions, to name but a few examples. Exemplary enterprise application suites include, without limitation, Oracle Fusion, Oracle eBusiness Suite and JD Edwards Enterprise One, all of which are available from Oracle Corporation of Redwood Shores, Calif.
For the purposes of explanation, one or more embodiments are illustratively described with reference to CRM applications. It is noted, however, that the invention may be applied to other types of enterprise applications as well, and is not to be limited to CRM applications unless explicitly claimed as such.
The analysis results 110 are stored into a database in a computer readable storage device 116. The computer readable storage device comprises any combination of hardware and software that allows for ready access to the data that is located at the computer readable storage device. For example, the computer readable storage device could be implemented as computer memory operatively managed by an operating system. The computer readable storage device could also be implemented as an electronic database system having storage on persistent and/or non-persistent storage.
Author profiling is performed upon the received data at 204. Semantic analysis is performed upon the received data to implement author profiling. For example, latent semantic analysis (LSA), an advanced form of statistical language modeling, can be used to perform semantic analysis upon the author writings. This permits the system to understand the contextual and semantic significance of terms that appear within the social data. For example semantic analysis can be used to understand the difference between the term “Galaxy” used in the author writing for astronomy content, and “Galaxy” in the author writing to refer to the name of a professional soccer team.
The system performs semantic analysis and classification to the social media data to create and identify themes, and to cluster together like-minded messages, topics, conversations, and content from the authors. This action is performed by categorizing the subjects of the author writings.
Strength numbers may be formed and associated with the different categories. The strength numbers indicate the extent or degree of affinity and/or interest by the author for any particular subject relative to other subjects. Using these strength numbers, a vector can therefore be defined for each author that establishes a profile of the interest for that author.
In some embodiments, the social data content is subject to semantic filtering to reduce the excess “noise” of irrelevant data. Semantic filtering is a mechanism that is provided to minimize miss-categorizations of the social data. Much of the social data is likely to contain content which is of very little interest. Semantic filtering is used to remove the irrelevant material from the social data to reduce the occurrence of false positives, false negatives, and inappropriate responses/rejections within the actionable data. This permits the resulting data to be more relevant and accurate.
The profiling process is repeated for numerous authors identified from the social media sources. At the end of this process, the analysis results will include vector data for numerous authors, where the vectors indicate the affinities between the authors pertaining to common topics or subjects.
For example, it may be of interest for businesses to know about the demographic class of consumers that are female authors who write messages on social media about sports. In this case, the author vectors 206 can be used to identify the authors having an affinity for this subject. Thus, in one embodiment of the invention, a business may pre-configure these types of topics, and the author profiles are used to search for authors that correspond to the pre-configured topic categories. In an alternate embodiment, these subject areas are not pre-defined. Instead, the analysis results are reviewed to discover commonality of subject areas based upon the authors' written works.
To illustrate, as shown in
The clustered set of data for these authors can then be analyzed to identify other common areas of interest that may be revealed by the author profiles. By performing correlation analysis 208, it is possible to discover other areas of commonality between these authors. For example, review of the author profiles may reveal that a substantial percentage of these authors also watch the “XYZ” TV show and have shown an interest in the “ABC” food product.
This type of correlation data is quite useful to a business organization. For example, businesses that market the “ABC” food product, or its competition, can use this information to specifically target this demographic group for its marketing campaigns. In addition, since the business knows this demographic group tends to watch the “XYZ” TV show, an effective advertisement campaign may be implemented by purchasing commercial advertisement time for this TV show or by providing advertisements on the website and/or Facebook for the show.
For many reasons, this approach provide much better analysis results when compared against the prior art approach of using surveys. Since the analysis is based upon the authors' own writings, the analysis results will produce much more accurate results when compared to the typical voluntary survey responses. Moreover, the present approach allows analysis to be performed over a very broad proportion of the general public, especially as compared to surveys that tend to have very limited response rates.
In addition, prior art surveys are often targeted at specific demographic groups of consumers, which may erroneously filter out other consumers that should be included within the target audience for a business. The present invention can be directed at the general public, ensuring that the broadest possible group of consumers is included in the analysis results.
The present approach is particularly useful at discovering correlations between consumers, even where those correlations are not known or expected upfront. This is because the semantic analysis and correlation process will cluster like-authors together using the contents of the author's own writings, without pre-conceptions about the subjects of those writings. As such, serendipitous discoveries are likely to occur from the disclosed author analysis.
At 304, themes analysis is performed for the writings by the authors. Based upon the semantic analysis and classification, themes are identified within the authors' works. These themes can be used to establish profiles for the authors.
At 306, the author profiles are analyzed to identify correlations between the different authors. For example, authors that have written about similar topics may be reviewed to identify other areas of commonality between those authors.
At 308, actionable data is generated for those authors. The actionable data correspond to areas of analytical importance with respect to the specific organizations that will be consuming the results of the system. For example, a business may seek to use the system to analyze author writings to (1) identify sales leads and (2) identify customer relations issues and dissatisfied customers. If these are the business' goals, then at least some of the analysis results will, in some embodiments, correspond to identification of the content that pertain to these categories, e.g., the information can be used to direct sales leads to the appropriate sales department.
The actionable data can be processed using any suitable processing mechanism. In one embodiment, automated processing is performed using a rules and workflow engine. In this approach, a set of rules is provided in a rulebase, where the rules identify how the actionable data should be handled and directed within the organization. The system then dispatches and/or creates the appropriate messages to be sent to destinations within the enterprise. For example, opportunity messages can be sent to a CRM system, where a record is automatically created and/or process in the system for the sales lead. Product data and comments can be provided to ecommerce products and groups. The present invention can therefore be used to provide a framework for integrating a corporate infrastructure to analysis results from the author profiling tool.
At 404, specific themes are identified within the author writings. The themes are identified based upon the topics and subjects revealed from the semantic analysis and classification process. Therefore, categorization is performed upon the subjects of the author writings. At 406, strength numbers are associated with the different categories that correspond to the authors. These strength numbers indicate the relative affinity of each author to a particular topic, subject, or theme.
At 408, a vector can then be defined for each author using the strength numbers for the different categories. The vector establishes a profile of the interests for that author, and can be used to describe and analyze that author with respect to the author's interests.
The author profiles may be used to identify a large grouping of authors that correspond to similar areas of interests. Therefore, at 410, the vectors can be correlated to perform commonality analysis among the authors. As noted above, the results from performing this type of correlation can be very useful to a business organization, e.g., for marketing or customer service purposes.
Therefore, what has been described is an improved system, method, and computer program product for analyzing interests of consumers, where semantic analysis is performed on writings by authors on social media sites. The results of the semantic analysis provide a profile of the authors. These author profiles can be used to identify and correlate topical interests by consumers. An enterprise or business can more effectively market to the consumers based upon this knowledge of the consumers' interests.
According to one embodiment of the invention, computer system 1400 performs specific operations by processor 1407 executing one or more sequences of one or more instructions contained in system memory 1408. Such instructions may be read into system memory 1408 from another computer readable/usable medium, such as static storage device 1409 or disk drive 1410. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions to implement the invention. Thus, embodiments of the invention are not limited to any specific combination of hardware circuitry and/or software. In one embodiment, the term “logic” shall mean any combination of software or hardware that is used to implement all or part of the invention.
The term “computer readable medium” or “computer usable medium” as used herein refers to any medium that participates in providing instructions to processor 1407 for execution. Such a medium may take many forms, including but not limited to, non-volatile media and volatile media. Non-volatile media includes, for example, optical or magnetic disks, such as disk drive 1410. Volatile media includes dynamic memory, such as system memory 1408.
Common forms of computer readable media includes, for example, floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, RAM, PROM, EPROM, FLASH-EPROM, any other memory chip or cartridge, or any other medium from which a computer can read.
In an embodiment of the invention, execution of the sequences of instructions to practice the invention is performed by a single computer system 1400. According to other embodiments of the invention, two or more computer systems 1400 coupled by communication link 1415 (e.g., LAN, PTSN, or wireless network) may perform the sequence of instructions required to practice the invention in coordination with one another.
Computer system 1400 may transmit and receive messages, data, and instructions, including program, i.e., application code, through communication link 1415 and communication interface 1414. Received program code may be executed by processor 1407 as it is received, and/or stored in disk drive 1410, or other non-volatile storage for later execution.
In the foregoing specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. For example, the above-described process flows are described with reference to a particular ordering of process actions. However, the ordering of many of the described process actions may be changed without affecting the scope or operation of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than restrictive sense.
