An empirical study of the structure of relevant keywords in a search engine using the minimum spanning tree

This paper provides a comprehensive study of the structure of relevant keywords in a search engine using the minimum spanning tree (MST) approach. In the process of constructing MST’s, we introduce a novel metric to measure a distance between keywords by applying an integration of the Pearson correlation and the query-based cosine similarity. From this work, we made several meaningful observations about the networks of relevant keywords. First, keyword networks in a search engine exhibit the small-world effect and the scale-free property. Second, only a few among relevant keywords in the order of popularity are positively correlated and there is no significantly positive or negative relationship for the rest of relevant keywords. Third, the degree of searching activity for relevant keywords varies depending on whether they are branded keywords or non-branded keywords as well as the characteristics of product categories. Fourth, the mean correlation coefficient for keyword impressions during slow season increases. Finally, both k_max and the betweenness centrality for high-involvement products are higher than those for low-involvement products.     

An empirical test to measure the effectiveness of online advertising in online marketplaces using a hierarchical Bayes model

Online marketplace, taken the form of “open market” where a very large number of buyers and sellers participate, has occupied a rapid increasing position in e-commerce, which resulting in sellers’ increasing investment on online advertising. Hence, there is a growing need to identify the effectiveness of online advertising in the online marketplaces such as eBay.com. However, it is problematic to directly apply the existing online advertising effect models for click-through data of online marketplaces. Therefore, there is a need for developing a model to estimate the effectiveness of online advertising in online marketplace considering its characteristics. In this paper, we develop an analytical Bayesian approach to modeling click-though data by employing the Poisson-gamma distribution. Our results have implications for online advertising effect measurement, and may help guide advertisers in decision-making.     

Search advertising placement strategy: Exploring the efficacy of the conventional wisdom

Search advertising is one of the most important forms of electronic commerce. While click-through rates are considered a key measure of search advertising effectiveness by search providers, brand attention can also be a valuable objective. Our paper reports on an experiment that investigated how search advertisement placement affected search users’ brand recall and recognition. The results showed that semantically associated search ads generated significantly higher levels of brand attention than contextually associated ones. Significant interaction effects were found among search ad position, keyword association, and search result quality. Implications for decision makers are discussed.     

A cross-industry analysis of the spillover effect in paid search advertising

For the management of paid search advertising campaigns, metrics collected at keyword-level are often used in practice whereas the users’ search process is of secondary importance and thus wholly or partially neglected. In contrast to brand-related keywords (“T-mobile contract”), general keywords, often referred to as generic (“mobile phone contract”), seem at first glance to be economically unattractive. Extending the approach of Rutz and Bucklin, Journal of Marketing Research, 48(1):87–102 (2011), we investigate the role of generic search activities in paid search advertising across industries using dynamic linear models (DLM). The so-called spillover effect, i. e. the increase in brand-related awareness effected by displaying ads for generic keywords, is investigated by both analyzing individual consumer behavior on the basis of keyword-level data and linking findings on keyword- with findings on individual user-level data. We show that the spillover effect varies across industries and that its consideration, for example for the mobile phone provider investigated here, decreases KPIs such as the cost per order up to 42 %.     

Modeling the clickstream across multiple online advertising channels using a binary logit with Bayesian mixture of normals

The evaluation of online marketing activities using standalone metrics does not explain the development of consumer behavior over time, although it is of primary importance to allocate and optimize financial resources among multiple advertising channels. We develop a binary logit model with a Bayesian mixture approach to demonstrate consumer clickstreams across multiple online advertising channels. Therefore, a detailed user-level dataset from a large financial service provider is analyzed. We find both differences in the effects of repeated advertisement exposure across multiple types of display advertising as well as positive effects of interaction between display and paid search advertising influencing consumer click probabilities. We identify two consumer types with different levels of susceptibility to online advertising (resistant vs. susceptible consumers) and show that the knowledge of consumers individual click probabilities can support companies in managing display advertising campaigns.     

Performance analysis of keyword advertising campaign using gender-brand effect of search queries

In this research, we analyze the relationship among (1) the performance metrics of a sponsored search campaign, (2) the gender orientation of queries, and (3) the occurrence of branded terms in queries. The aim of this research is to investigate the effectiveness of increased personalization of search engine advertising in order to improve the consumer’s online experience. We segregate keyphrases from a dataset covering thirty-three consecutive months from a major US retailer consisting of 7 million daily records of a real time keyword advertising campaign into three gender categories (male, female and neutral) each with two groups (branded and unbranded) term usage. Using ANOVA, we analyze the effect of gender and brand keyphrases on critical sponsored search performance metrics of impressions, clicks, cost-per-clicks, sales revenue, orders, items purchased and return on advertising. Research findings show that the combination of brand focus with the gender-orientation of keyphrases is a significant factor in predicting sponsored search performance and behavior. There are statistically significant variations in consumer behavior as measured by sponsored search metrics among the gender categories. Specifically, females are more attracted to the use of branded terms than males, perhaps due to the trust and customer loyalty generated by brand image. Our results establishes that positive brand reputation creates dramatic influence on consumer’s loyalty over the brand and hence strongly affects their interests, activities and purchasing behavior in e-commerce environment.     

网络广告关键词选择优化

搜索引擎广告系统的核心任务是针对用户提交的每个查询,决定以何种顺序显示哪些广告。这是广告商和搜索引擎之间的一个博弈过程：搜索引擎需要准确地估算广告的点击率,提高广告收益、广告商的满意度及用户的满意度;广告商则需要猜测搜索引擎的排序模型、竞价广告栏并依据广告效果调整广告策略以及执行其他的搜索引擎优化动作。探讨了推测CPC模式下搜索引擎广告排序模型的一般方法,并据此指导广告商的关键词选择策略。     

An analysis of the importance of the long tail in search engine marketing

Search engine marketing is currently the most popular form of online advertising. Many advertising agencies and bloggers claim that the success of search engine marketing is driven by the “long tail”, defined in this research as the many less popular keywords employed by users to search the Internet, and suggest that search engine marketing campaigns need to have hundreds or thousands of keywords to accommodate this phenomenon. We doubt this claim. Our data from three search engine marketing campaigns in two countries, which report the success of a total of 4908 keywords over 36 weeks, covering 10,104,015 searches and 492,735 clicks, show that the top 20% of all keywords attract on average 98.16% of all searches and generate 97.21% of all clicks. The use of the top 100 keywords in each campaign attracts on average 88.57% of all searches and 81.40% of all clicks. These results are fairly stable across a varying total number of keywords in use and suggest that the success of search engine marketing is driven by relatively few keywords. However, we also show that the set of the top 100 keywords changes over time. Hence, advertisers need to concentrate on finding the top 100 keywords, but they do not need to bother too much about the performance of keywords in the long tail.     

Online keyword based advertising: Impact of ad impressions on own-channel and cross-channel click-through rates

Keyword-based ads are becoming the dominant form of advertising online as they enable customization and tailoring of messages relevant to potential consumers. Two prominent channels within this sphere are the search channel and the content channel. We empirically examine the interaction between these two channels. Our results indicate significant cannibalization across the two channels as well as significant diminishing returns to impressions within each channel. This suggests that under certain conditions both channels may need to be used to optimize returns to advertising both for advertisers and service providers such as Google. Our game theoretic analysis which builds upon our empirical findings reveals that for intermediate budget values it is optimal to use both channels whereas for very low (very high) budget values it is optimal to use only the content (search) channel. Further as budget increases the advertiser should offer more for ads displayed on the search channel to optimally incentivize the service provider.     

An examination of the celebrity endorsements and online customer reviews influence female consumers’ shopping behavior

The goal of this study is to compare the influence of celebrity endorsements to online customer reviews on female shopping behavior. Based on AIDMA and AISAS models, we design an experiment to investigate consumer responses to search good and experience good respectively. The results revealed that search good (shoes) endorsed by a celebrity in an advertisement evoked significantly more attention, desire, and action from the consumer than did an online customer review. We also found that online customer reviews emerged higher than the celebrity endorsement on the scale of participants’ memory, search and share attitudes toward the experience good (toner). Implications for marketers as well as suggestions for future research are discussed.     

The effect of negative online consumer reviews on product attitude: An information processing view

Online consumer reviews provide product information and recommendations from the customer perspective. This study investigates the effects of negative online consumer reviews on consumer product attitude. In particular, it examines the proportion and quality of negative online consumer reviews from the perspective of information processing. The elaboration likelihood model is used to explain the persuasive effect of the proportion and quality depending on product involvement. A high proportion of negative online consumer reviews elicits a conformity effect. As the proportion of negative online consumer reviews increases, high-involvement consumers tend to conform to the perspective of reviewers, depending on the quality of the negative online consumer reviews; in contrast, low-involvement consumers tend to conform to the perspective of reviewers regardless of the quality of the negative online consumer reviews. The experiment in this study uses 248 college students in Korea. The proposed hypotheses are tested by three-way analysis of covariance.     

Volunteers’ involvement in online community based software development

We sought to gain understanding of voluntary developers’ involvement in open source software (OSS) projects. Data were collected from voluntary developers working on open source projects. Our findings indicated that a voluntary developer's involvement was very important to his or her performance and that involvement was dependent on individual motivations (personal software needs, reputation and skills gaining expectation, enjoyment in open source coding) and project community factors (leadership effectiveness, interpersonal relationship, community ideology). Our work contributes theoretically and empirically to the body of OSS research and has practical implications for OSS project management.     

Effect of metacognitive strategies and verbal-imagery cognitive style on biology-based video search and learning performance

Videos have diverse content that can assist students in learning. However, because videos are linear media, video users may take a longer time than readers of text to evaluate the context. Therefore, the process of video search may vary from one user to another depending on the users' individual characteristics, and the effectiveness of video learning may also vary across individuals. This study evaluated 100 Taiwanese fifth graders searching for videos related to “understanding animals” on YouTube and examined the effects of the students' metacognitive strategies (planning, monitoring, and evaluating) and verbal-imagery cognitive style on their video searches. The observable indicators were quantitative (search behaviors, search performance, and learning performance) and qualitative (search process observations and interviews). The study concludes that metacognitive strategy is the primary influencer of video search. Students with better metacognitive skills used fewer keywords, browsed fewer videos, and spent less time evaluating videos, but they achieved higher learning performance. They reviewed the video metadata information on the user interface and did not attempt to watch videos on the video recommendation lists, particularly videos that were irrelevant to the task requirements. During the course of the searches, keyword usage had a significant influence on the students' search performance and learning performance. The fewer keywords the students used, the better search and learning performance they were able to achieve. Our results are different from those of previous studies on text, image, and map searches. Accordingly, users must adopt different search strategies when using various types of search engines.     

Exploiting the Community Structure of Fraudulent Keywords for Fraud Detection in Web Search

Internet users heavily rely on web search engines for their intended information.The major revenue of search engines is advertisements (or ads).However,the search advertising suffers from fraud.Fraudsters generate fake traffic which does not reach the intended audience,and increases the cost of the advertisers.Therefore,it is critical to detect fraud in web search.Previous studies solve this problem through fraudster detection (especially bots) by leveraging fraudsters' unique behaviors.However,they may fail to detect new means of fraud,such as crowdsourcing fraud,since crowd workers behave in part like normal users.To this end,this paper proposes an approach to detecting fraud in web search from the perspective of fraudulent keywords.We begin by using a unique dataset of 150 million web search logs to examine the discriminating features of fraudulent keywords.Specifically,we model the temporal correlation of fraudulent keywords as a graph,which reveals a very well-connected community structure.Next,we design DFW (detection of fraudulent keywords) that mines the temporal correlations between candidate fraudulent keywords and a given list of seeds.In particular,DFW leverages several refinements to filter out non-fraudulent keywords that co-occur with seeds occasionally.The evaluation using the search logs shows that DFW achieves high fraud detection precision (99％) and accuracy (93％).A further analysis reveals several typical temporal evolution patterns of fraudulent keywords and the co-existence of both bots and crowd workers as frandsters for web search fraud.     

基于LDA的互联网广告点击率预测研究

广告点击率是互联网广告投放的重要依据,有效地预测广告的点击率,对于提高广告投放的效率有着至关重要的作用。在训练点击率预测模型的过程中,往往面临着广告及用户的数量巨大以及训练数据集稀疏的问题,从而导致点击率预测的准确度下降。针对这些问题提出了一种基于LDA (Latent Dirichlet Allocation)的点击率预测算法,即LDA-FMs,该算法对原有训练集进行基于主题的分割,利用分割后的子训练集分别建立不同主题下的点击率预测模型,在此基础上,利用广告属于不同主题的概率,有权重的结合每个预测模型的预测结果,进而计算广告的点击率。实验基于KDD Cup 2012-Track2的真实数据集,证明了算法的可行性与有效性。     

基于关键字关联及节点兴趣的搜索机制

P2P节点用户的搜索内容在一定程度上体现了用户的兴趣.为此,提出一种基于关键字关联和节点兴趣的P2P信息搜索机制.该机制注重关键字之间关系的学习,通过用户操作发现节点兴趣.在搜索中利用关键字的语义关系增加命中目标,提高搜索成功率.根据节点兴趣缩小搜索范围、降低搜索开销.实验结果表明,采用快速建立索引表的方法和反馈机制能...     

Assessing the impact of recommender agents on on-line consumer unplanned purchase behavior

Recommendation agents (RAs) have been used by many Internet businesses such as Amazon and Netflix. However, few authors have studied how consumer behavior is affected by those that make suggestions to online consumers based on their recent shopping behavior. Fewer still have examined the role that RAs play in influencing impulse purchasing decisions online. Our study developed a theoretical model to illustrate the impact of RAs on online consumer behavior. The model was tested through an online shopping simulation which used a collaborative filtering based product RA. Particular attention was paid to the effects of an RA on consumer behavior; we found that it increased promotion and product search effectiveness, user satisfaction with the website, and unplanned purchases. Results showed that our model provided insights into the impact of an RA on online consumer behavior and thus provided suggestions for implementing effective systems.     

Can avatar and self-referencing really increase the effects of online 2-D and 3-D advertising?

Previous studies have sought insights into how websites can effectively draw sustained attention from internet users. Do different types of information presentations on webpages have different influences on users’ perceptions of the information? More precisely, can combinations of an ever greater number of advertising elements on individual websites increase consumers’ purchase intentions? The aim of this study is to explore changes in web advertising’s verbal and visual stimulation of surfers’ cognitive process, and to provide valuable information for the successful matching of advertising elements to one another. We examine optimal website design according to the personality-trait theory and resource-matching theory. Study 1 addresses the effects that combinations of various types of online advertising can have on web design factor, and to this end, we use a 2 (visual complexity: 3D advertising with an avatar, 2D advertising) × 2 (verbal complexity: with or without self-referencing that is an advertising practice to express product claims in words) factorial design. Study 2 treats personality traits (i.e., need-for-cognition and sensation seeking) as moderating variables to build the optimal portfolio regarding the “online-advertising effects” hypothesis. Our results suggest that subjects prefer medium-complex advertising comprising “3D advertising elements with an avatar” or “2D advertising elements with self-referencing”: high-sensation seekers and low-need-for-cognition viewers prefer the former, whereas low-sensation seekers and high-need-for-cognition viewers prefer the latter.     

eWOM overload and its effect on consumer behavioral intention depending on consumer involvement

Online consumer reviews involving experiences, evaluations and opinions on products from previous consumers play two roles – an informant and a recommender. These two roles affect a consumer’s intention. However, there is a conflict between two roles when a large number of reviews are offered. From the perspective of the recommender role, consumers have more favorable attitude toward a product as a greater number of positive reviews are offered while consumers may be confronted with too much information, which results in information overload. This study investigates what consequences the tradeoff between two roles has on purchasing intention depending on consumer involvement.