Introduction

The collaborative web or Web 2.0 as it is addressed has provided additional touchpoints for organizations, hence aiding customer centricity, and providing opportunities for usage of consumer-generated data for customer relationship management (CRM). While increasing interactivity with the consumer helps build consumer engagement, of substantial importance is the analysis of data generated by the consumers. Corporate blogs are frequently utilized by organizations for increasing the perceived value of the consumers by showcasing organizational, product and brand-related achievements, thereby enhancing the brand image, aiding consumer learning and also serving as a useful touchpoint to enhance the consumer-brand relationship. Usage of posts on corporate blogs to apprise consumers of new promotional campaigns and product launches is fast becoming a useful marketing and CRM strategy. Consumers can use the comments feature to voice product or service-related complaints, thereby increasing consumer involvement. These can be subsequently actioned by the organization.

This paper addresses the issue of extracting consumer-related information from the comments posted by consumers in response to an organizational post on a corporate blog. The consumer responses viz. consumer comments can be aggregated using tags and folksonomies and further mined to gauge consumer sentiment and to serve as a decision support system for better segmentation and response management. We also develop a conceptual framework to categorize consumer responses and redirect them to the CRM functionalities of campaign management, customer service and support, and support to marketing communication and product development.

Corporate blogging

Web 2.0 is a collection of open-source, interactive and user-controlled online applications expanding the experiences, knowledge and market power of the users as participants in business and social processes.1 These tools of the collaborative web have found applications in the corporate sector in the domains of Marketing, Brand Promotion and CRM.Web 2.0 also appears to have a substantial effect on consumer behaviour and on new challenges facing strategists and marketers.2 Corporate blogs, Online communities, social networks, wikis, micromedia and folksonomies are some Web 2.0 concepts being used by businesses.

The dictionary meaning of a blog is a frequent, chronological publication of personal thoughts and links. As millions of people use blogs as personal diaries on the internet, they are emerging as collaborative spaces that can be put to multiple uses and have emerged as the latest mode of computer-mediated communication.3 This concept has found widespread acceptance in the corporate world with the emergence of ‘corporate’ or ‘organizational’ blogs. These are people who blog in an official or semi-official capacity at a company, or are so affiliated with the company where they work that even though they are not officially spokespeople for the company they are clearly affiliated4 and endorsed explicitly or implicitly by the company. Also termed as a hybrid of the personal blog,5 they are increasingly being explored by public relations practitioners and feature the insights, assessments, commentary and other discourse devoted to a single company. Organizational blogs have evolved from both online and off-line modes of communication and have characteristics of both personal and professional communication.6 An effective blog fosters community and conversation,7 drives traffic to the product website, and serves as a medium for interaction with consumers, thereby shaping consumer perception, eliciting responses, and through a two-way thought exchange process aids in fostering a connection with the consumers. External Corporate blogs are primarily tools used by organizations to interact with consumers, partners, marketing intermediaries, associates and components of the external environment viz. media, government agencies and other general bodies. They offer a more up-to-date view of the organization as compared to other traditional communication channels. Tapping into this new channel to listen to and interact with their customers requires new initiatives from corporations.8 They further provide a tremendous opportunity for forward-thinking companies and management to have a significant positive impact on their public perception. Launching a corporate brand blog is representative of an organizational desire to share information and engage in a conversation. This is especially true when the blog allows visitors to post their own comments. The informality of communication helps companies build trust,9 converse with people and even manage public perception by posting suitable responses. The ability of a blog to induce consumer participation by making consumers comment on the posts hosted by the organization creates a dialogue and helps the organization achieve consumer engagement. By further varying the content typologies, organizations can engage in maintaining good consumer relationships by better content management.10

While the ability of a blog to achieve higher volumes of engagement in terms of volume of comments is significant, of greater importance is the knowledge capital created through exchange with consumers, which can be mined to extract explicit information that can be leveraged by the organization as a decision support system for consumer segmentation and strategy formulation. For the purpose of this study, we focus on external blogs being used by organizations to build brand relationships with consumers and induce participation and engagement.

CRM

We explore the usage of a blog as a CRM tool. CRM, which has also been described as ‘information-enabled relationship marketing’,11 is an enterprise-wide initiative that belongs to all areas of an organization.12 It comprises processes used by organizations to manage consumer relationships, which also include collecting, storing and analysing data and attempts to provide a strategic bridge between IT tools and marketing strategies aimed at building long-term relationships and profitability. A blog can be used by an organization to acquire customer information and consolidating customer feedback.

Companies can use a blog to interact with customers, learn about them and through the process of incorporating feedback and co-creation develop a level of intimacy with them. This can help improve marketing intelligence and support decision making. Consumer-specific data can help in targeting the appropriate set of consumers with the appropriate marketing campaigns. These consumer data can be obtained by analysis of consumer-generated content on a blog, in the form of comments.

Tagging and folksonomies

The emergence of new communication models resulting in increased informational and exchange needs, and the availability of incredible amounts of distributed information that can be linked, aggregated and organized in order to extract knowledge, has created the need to structure this information to derive meaning. Folksonomies attempt to provide a solution to this issue by introducing an innovative distributed approach based on social classification,13 hence addressing these web-specific classification issues. Folksonomy (also known as collaborative tagging, social classification, social indexing and social tagging) is the practice and method of collaboratively creating and managing tags to categorize content. Folksonomy describes the bottom-up classification systems that emerge from social tagging.14 Tags are created with the intent of signifying or suggesting concepts that are potentially or accompanying or associated with possible content ontologies. If consumers can be allowed to tag their comments, a better aggregation of user-generated information can be achieved to serve as an aid in response modelling. This requires consumers to associate keywords with content. The best judge of classification of one's comment under a blog post would be the consumer himself, who can tag his comment with the closest possible option available from an organization-specified list. Tags are inexpensive, scalable and very near the language and mental mode of the users. If consumers tag the comments themselves, relevance and consistency of the relation of the content in the comment to the tag will be greater. Problems pertaining to lack of terminological control in the tags can be omitted by allowing consumers to choose from a predefined list only. Grouping tags under folksonomies related to consumer liking, satisfaction and involvement aids data redirection to respective CRM functionalities. Further, a quantitative tag analysis can help explain the dominant consumer viewpoint.

Campaign management

Some functions performed by a Campaign management solution include:

  1. i)

    segmentation of customers;

  2. ii)

    developing targeting and positioning strategies for each segment;

  3. iii)

    defining customer requirements;

  4. iv)

    implementing communication strategies to build brand awareness, generate interest and motivate purchase.15

Often, due to lack of data regarding the consumer sentiment for the organization and its products, organizations resort to blanket promotions for their consumers, thereby not matching the true consumer expectations. CRM entails constant integration of marketing, sales and service activities, and applying customer knowledge to continuously improve performance.16 A corporate blog can be used to increase the knowledge and understanding of customers,17 and can be utilized for campaign management18 by segmenting groups of customers (and prospective customers) into smaller groups by identifying and understanding unique customer patterns and then specifying the interaction that should take place with those individuals, by creation of customized offers.

Sentiment mining

Sentiment mining is a computational approach used to identify expressions made about topics within a span of text.19 With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people can now, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object.20 Given an opinionated piece of text wherein it is assumed that the overall opinion in it is about one single issue or item, it is possible to classify the opinion as falling under one of two opposing sentiment polarities, or locate its position on the continuum between these two polarities.21 This concept of sentiment mining is adapted for mining sentiment of consumers, as represented by their comments under an organizational blog post to determine positive or negative sentiment polarity.

Using a corporate blog as a CRM 2.0 tool

Methodology

Leveraging the power of folksonomies

We propose a system where consumers are allowed to tag their comments, from a set of organization-defined options, which would enable aggregation of user-generated information to serve as an aid in better response management. The objective is to derive a model to assign each comment to a class as accurately as possible. Allowing a consumer to tag his comment will enable classification under the theme that most closely reflects the consumer intent, thereby enabling a better aggregation of content reflected in the comments section located under each blog post. Twenty-four comment typologies have been observed. A tag representing each comment typology can be created by the consumer for his comment whenever he interacts with the organization. By allowing the consumers to tag the comments, under respective categories using tags viz. liking, feedback, appreciation, praise, happiness, approval, anger, disappointment, etc better content aggregation is possible (Table 1).

Table 1 Comment typologies and sentiment bearing words
Full size table

Further, it is possible to identify sentiment-bearing words depicting respective sentiments, from consumer comments posted under the blog posts hosted by the organization.

Clustering of these tags under folksonomies of liking, satisfaction, dissatisfaction or involvement with the organization/product can aid in routing comments under the tags to the respective CRM functionalities. This can be done using a factor analysis. Therefore, a folksonomy can be a low-cost community option for response modelling. A factor analysis helped load the diverse comment typologies onto six different factors (Table 2): Liking, Satisfaction, Involvement I, Involvement II, Involvement III and Involvement IV.

Table 2 Rotated component matrix
Full size table

Involvement I-IV together represent various levels of consumer involvement. It is further possible to segment consumers on the basis of their sentiment score as lying on the continuum between liking, satisfaction and involvement. Hence, tags can be created for aggregation of consumer comments and folksonomies can be used to extract information from tags and the same can be diverted to the respective functions in an organization for response modelling.

Customer liking, satisfaction and involvement

A consumer passes through several stages viz. liking, satisfaction and involvement in his relationship with the organization. Liking can be defined as a state of fondness, affection or preference for product, brand or organization. This is a preliminary stage of consumer developing a tertiary interest in a product. A consumer moves to the next stage when he starts perceiving greater value in an organizational offering. The perceived value is now equated with perceived quality by customers and due to this customer satisfaction is enhanced.22 This improves as firms customize offerings for customers and further when firms improve the reliability of consumption experiences by ensuring timely processing of various customer requests. Consumers also tend to express their happiness and appreciation in the relationship with the organization and brand. This expression can be treated as representative of consumer satisfaction. IT tools can help in this regard. Consumer involvement is the perceived personal importance and/or interest attached to the acquisition, consumption and disposition of a good service or idea.23 As involvement increases, the consumer has greater motivation to comprehend and elaborate on information. Several factors influence the level of the consumer's involvement: type of product being considered, characteristics of the communication received by the consumer, characteristics of the situation within which the consumer is operating, personality of the consumer and exposure to information or product usage. At times, consumers depict a consistent high-level interest in a product and frequently spend time thinking about the product. As the consumer involvement levels increase, consumers tend to process more product- and brand-related information, and are likely to give more diligent consideration to information relevant to a particular decision. By identifying the level of consumer involvement, organizations can formulate strategies accordingly. While high-involvement segments may be early adopters, others may have more extended decision-making processes. For the purpose of response management, four levels of consumer involvement are identified from the consumer comment typologies. Consumers who express doubt or worry regarding a product, brand, features etc are considered to be on the low end of the involvement scale. The next level represents consumers who have a complaint and seek grievance redressal, followed by those who have suggestions for marketing and corporate communications. The consumers who provide feedback in response to an organizational request or suggestions by a personal initiative with regard to product features and scope for improvement are considered to be highly involved with the organization.

Evaluating consumer sentiment using Sentiwordnet 1.0

For evaluating consumer sentiment, we use Sentiwordnet 1.0,24 a lexical resource in which each WORDNET synset is associated with numerical scores Obj(s), Pos(s) and Neg(s), describing how objective, positive and negative the terms contained in the synset are. Considering comments as sets of opinionated text, with the assumption that the text (each set of comments on a single post) is related to a single issue or item, it may be interesting to see that the opinion would be either positive or negative or feature somewhere on the continuum between these two polarities. This can be done by converting each comment into a feature vector by using a text processing tool and then identifying the sentiment bearing features. By using a sentiment mining tool, where each opinionated word has been allocated a sentiment score on the basis of its wordnet synset, a sentiment score can be calculated for each individual comment. In this context, term occurrence has to be used as an indicator, and not term frequency, because in traditional sentiment classification increased term occurrence does not emphasize/change the sentiment polarity. Further, considering the algebraic sum of the term orientations as representative of the sentiment behind the comment, the score can be calculated. It is important here to correlate each term to the correct wordnet synset it belongs to, as that holds the key to the score. Volumes of consumers depicting positive and negative sentiment polarity are calculated.

Consumer segmentation based on consumer sentiment score

By using corporate blogs for segmentation, marketing managers can segment customers (and prospective customers) into smaller groups and then specify the interaction that should take place with those individuals. Segmentation is the process of identifying groups of customers around whom to conduct marketing efforts by analysing the existing customer base. It is a very important functionality of any tool as this allows the marketing manager to fine-tune the deliverables of the campaign. While this helps in identifying most appropriate targets for specific campaigns by understanding a consumer's relationship with the organization, it also aids the process of consumer retention by identifying consumer groups that need special attention or redressal.

Traditionally, only a few broad segments could be defined based on overall demographic information. With changing times, as volumes of data being collected internally have grown, it is possible to define many more segments at a finer level of granularity. In addition, it is now possible to define the segments based on their actual interaction with the company (rather than general demographic information) and to automate different responses to each segment. These consumer comments on the organizational blog posts conceal a wealth of information. While consumers with positive sentiment polarity can be subjected to consumer acquisition strategies, consumers with negative polarity represent a state of consumer dissatisfaction and can be subjected to strategies for consumer retention. All consumers falling under the 0 to 0.5 bracket are assumed to represent a state of liking. All consumers having a score of more than 0.5 can be assumed to represent a state of satisfaction. Consumers with comments classified under involvement are segmented separately and assigned a score of 1 for ease of tabulation.

Measuring campaign effectiveness I

Campaign effectiveness can be calculated on the basis of:

  1. i)

    Mean sentiment score for individual campaign — Effectiveness of individual campaign can be calculated by calculating the mean sentiment score of each campaign. As per the central limit theorem in statistics, the distribution of these mean sentiment scores across various campaigns reflects the average of the entire population.

  2. ii)

    Volume of consumers demonstrating positive and negative sentiment polarity.

Measuring campaign effectiveness II — Quantitative tag analysis

A quantitative tag analysis for tags representing comments under each post can help generate a tag cloud that can further help understand the dominant consumer viewpoint.

Tag frequency — Inverse blog frequency

We use a variation of the TF-IDF (Term Frequency-Inverse Document Frequency) criteria, often used in information retrieval and data mining. We use this as a statistical measure to evaluate the results of a particular campaign represented by a post. The number of comments under a particular tag representing the comments for a blog post will be represented by a numerical figure (equivalent to term frequency). This will be indicative of the number of consumers adhering to a particular comment typology, thereby representing the thought process of the population. However, as a tag with the smallest comment frequency (volume of comments) may represent the most meaningful input, it may make sense to weight the same through the concept of inverse blog frequency. Hence, an inverse blog frequency factor can be incorporated, which can diminish the weight of the most commonly used tags, to offset the importance of the most commonly occurring terms by increasing the weight of the tags that may be used rarely but would hold meaningful information for the organization.

Tag frequency=(Frequency of Comments under Tag i in Post j)/(total no. of comments across all tags for post j)

Inverse blog frequency=log (total no. of posts in a corpus(blog)/no. of posts where a tag appears)

Then TF-IBF can be calculated by Tag frequency × Inverse tag frequency

A high-weight TF-IBF is reached by a high-tag frequency and a low frequency of the tag in the complete set of posts in the blog.

Hence, the value of a tag, hence representative of the consumer set it denotes appears:

  1. i)

    to increase proportionally to the no. of times a consumer posts a comment in that typology

  2. ii)

    but is offset by the frequency of that tag usage in the entire blog (percentage of blog posts the tag appears in)

  3. iii)

    This can be used to create a tag cloud for each campaign (blog post). Tag clouds are visualizations of tag frequencies. In this case, a tag cloud for the consumer comments on a blog post (campaign) will reflect the predominant consumer thought, represented by the tag with the maximum frequency of consumer comments in response to the post (campaign).

Determination of intercampaign similarity

The TF-IBF measure can be used to determine similarity of results (consumer thought process as represented by the comments under the respective tags) between two blog posts (campaigns). For this purpose, cosine similarity can be used. Cosine similarity is the measure of similarity between two vectors of n dimensions by finding the cosine of the angles between them. By using the tag frequency vectors of two campaigns, cosine similarity method can be used to normalize the no. of comments in a post. With values of these similarity measures ranging between −1 and +1, determining the similarity between the responses to two campaigns can help organizations improve targeting of future campaigns.

The Cosine Similarity of two vectors (C1 and C2) can be defined as:

where C1 × C2=C11 × C21+C12 × C22… and where ||C1||=sqrt(C112+C122…)

Results

  1. 1)

    Folksonomies related to consumer liking, satisfaction and involvement are established. All comments tagged under the tag cluster visible under the folksonomies of liking and satisfaction can be diverted for sentiment mining to aid consumer segmentation. All comments under the tag cluster representing the folksonomy of Involvement I and II are routed to the ‘Customer Service and Support’ functionality. All comments under the tag representing the folksonomy of Involvement III are directed to the ‘Marketing Communication’ function and all comments under the tags clustered under Involvement IV are sent to the ‘Product development’ function. (Figure 1)

    Figure 1
    figure 1

    CRM 2.0 — Using a corporate blog for campaign management

    Full size image
  2. 2)

    Results obtained from a study of a set of campaigns (promotional posts) hosted at Southwest blog are included below:

  1. a

    Term extraction and calculation of sentiment score for each consumer comment: Different comment typologies are established and the sentiment bearing words in each comment are identified, Table 1. Each individual comment here is assumed to reflect the thought process of a single consumer. The respective scores of words in each comment and the resultant sentiment score for each comment, reflecting individual consumer, is calculated. This is used to calculate the mean sentiment across each campaign, as represented by an organizational post.

  2. b

    A total of 396 consumers across 25 promotional campaigns (posts) were evaluated. Seventeen per cent consumers displayed negative sentiment and 83 per cent displayed positive sentiment. Fifty-seven per cent consumers displayed a sentiment score between 0 and 0.5. (Figure 2)

    Figure 2
    figure 2

    Consumer segmentation

    Full size image
  3. c

    The distribution of mean sentiment scores is shown in Figure 3.

    1. i)

      The mean of the population hovered around 0.23 (Table 3).

      Table 3 Distribution of mean sentiment scores across various campaigns (Mean sentiment score for 25 campaigns)
      Full size table
    2. ii)

      Consumer sentiment for individual ‘campaigns’ was a function of the respective campaigns.

    3. iii)

      No correlation was observed between no. of words per post and sentiment score of the campaign.

    Figure 3
    figure 3

    Distribution of mean sentiment scores across various campaigns

    Full size image
  4. d

    Tag dominance representing the tag dominating the view of the maximum no. of consumers can be analysed by studying a TF_IBF measure for each campaign. Tag clouds can be used to view the dominant consumer viewpoint.

  5. e

    Cosine similarity measures can be used to study similarity of responses between a set of campaigns, which can help predict consumer response to a particular campaign.

Conclusions

It is important for organizations to understand what their consumers are saying when they are interacting with them. We have demonstrated here the usage of corporate blog to extract and classify the consumer responses to posts hosted by an organization on the blog. By treating each post put up by the organization as a campaign and then using the comments to understand the dominant consumer viewpoint, companies can use this online tool to gauge the effectiveness of their campaigns. Companies can also segment the consumers on the basis of their sentiment scores and implement targeting strategies appropriately.

We have used this study to show that organizations can make use of the information available about their prospective and current customers by structuring and mining the vast volumes of data available on the web and formulate strategies for consumers by segregating them on the basis of some factors like the sentiment score represented in the discussion above. While consumers depicting a positive sentiment polarity can be grouped on the basis of their sentiment featuring on the continuum between liking and involvement, consumers with negative sentiment polarity, who are most likely to defect from the company, can be subjected to a well-directed retention campaign. Usage of a blog as a CRM tool can be achieved by routing the outcomes of the campaigns, represented by individual blog posts to the other organizational functions. By routing the aggregated consumer responses to functions of customer support, marketing etc, organizations can frame responses to the consumers or develop appropriate targeting strategies. Corporate blogs can definitely be used as Web 2.0 tools to become parts of successful CRM initiatives in organizations.