Search results

The purpose of this paper is to model group advertising decisions, which are the collective decisions of every single advertiser within the set of advertisers who are competing in the same auction or vertical industry, and examine resulting market outcomes, via a proposed simulation framework named Experimental Platform for Search Engine Advertising (EXP-SEA) supporting experimental studies of collective behaviors in the context of search engine advertising.

The authors implement the EXP-SEA to validate the proposed simulation framework, also conduct three experimental studies on the aggregate impact of electronic word-of-mouth (eWOM), the competition level and strategic bidding behaviors. EXP-SEA supports heterogeneous participants, various auction mechanisms and also ranking and pricing algorithms.

Findings from the three experiments show that both the market profit and advertising indexes such as number of impressions and number of clicks are larger when the eWOM effect is present, meaning social media certainly has some effect on search engine advertising outcomes, the competition level has a monotonic increasing effect on the market performance, thus search engines have an incentive to encourage both the eWOM among search users and competition among advertisers, and given the market-level effect of the percentage of advertisers employing a dynamic greedy bidding strategy, there is a cut-off point for strategic bidding behaviors.

This is one of the first research works to explore collective group decisions and resulting phenomena in the complex context of search engine advertising via developing and validating a simulation framework that supports assessments of various advertising strategies and estimations of the impact of mechanisms on the search market.

It is important to measure the interaction between conversing in social media and searching on the web in order to understand the impact on electronic word-of-mouth marketing. The paper aims to discuss this issue.

The authors research the relationship between social media conversing and web searching concerning brands on three major social soundtrack platforms (Instagram, Twitter, and Tumblr) and on a major web search engine (Google). The authors examine the effects of changes in both volume and attitude of conversing and volume of searching for two phases (Pre and Post) concerning brands in commercials aired during Super Bowl XLIX. The authors perform Granger causality testing and panel data regression analysis to determine the causal relationship between social media conversing and web searching.

Results show that volume and attitude of social media conversing has a significant causality relationship to the volume of web searching. Each unit increase of volume on Twitter, Instagram, and Tumblr significantly increases Google search volume for the same brands by 4.7 times, 11.9 times, and 8.7 times, respectively. Each unit increase of attitude score on Twitter significantly increases web search volume 3.96 times, while for Tumblr, search volume significantly increases 0.95 times with each unit. Interestingly, search volume also has a significant causality relationship on the volume of social media postings.

This research seeks to understand the commercial impacts of the interaction among broadcast advertising, social media conversing, and web searching for which there is limited prior work, especially in the context of a major media event.

Web search services are now a major source of information for a growing number of people. We need to know more about how users search Web search engines to improve the effectiveness of their information retrieval. This paper reports results from a major study exploring users’ information searching behavior on the EXCITE Web search engine. The study is the first to investigate Web users’ successive searching behavior as they conduct related searches

The “what is beautiful is good” (WIBIG) effect implies that observers tend to perceive physically attractive people in a positive light. The authors investigate how the WIBIG effect applies to user personas, measuring designers' perceptions and task performance when employing user personas for the design of information technology (IT) solutions.

In a user experiment, the authors tested six different personas with 235 participants that were asked to develop remote work solutions based on their interaction with a fictitious user persona.

The findings showed that a user persona's perceived attractiveness was positively correlated with other perceptions of the persona. The personas' completeness, credibility, empathy, likability and usefulness increased with attractiveness. More attractive personas were also perceived as more agreeable, emotionally stable, extraverted and open, and the participants spent more time engaging with personas they perceived attractive. A linguistic analysis indicated that the IT solutions created for more attractive user personas demonstrated a higher degree of affect, but for the most part, task outputs did not vary by the personas' perceived attractiveness.

The WIBIG effect applies when designing IT solutions with user personas, but its effect on task outputs appears limited. The perceived attractiveness of a user persona can impact how designers interact with and engage with the persona, which can influence the quality or the type of the IT solutions created based on the persona. Also, the findings point to the need to incorporate hedonic qualities into the persona creation process. For example, there may be contexts where it is helpful that the personas be attractive; there may be contexts where the attractiveness of the personas is unimportant or even a distraction.

The findings point to the need to incorporate hedonic qualities into the persona creation process. For example, there may be contexts where it is helpful that the personas be attractive; there may be contexts where the attractiveness of the personas is unimportant or even a distraction.

Because personas are created to closely resemble real people, the authors might expect the WIBIG effect to apply. The WIBIG effect might lead decision makers to favor more attractive personas when designing IT solutions. However, despite its potential relevance for decision making with personas, as far as the authors know, no prior study has investigated whether the WIBIG effect extends to the context of personas. Overall, it is important to understand how human factors apply to IT system design with personas, so that the personas can be created to minimize potentially detrimental effects as much as possible.

Web search engines are frequently used by people to locate information on the Internet. However, not all queries have an informational goal. Instead of information, some people may be looking for specific web sites or may wish to conduct transactions with web services. This paper aims to focus on automatically classifying the different user intents behind web queries.

For the research reported in this paper, 130,000 web search engine queries are categorized as informational, navigational, or transactional using a k‐means clustering approach based on a variety of query traits.

The research findings show that more than 75 percent of web queries (clustered into eight classifications) are informational in nature, with about 12 percent each for navigational and transactional. Results also show that web queries fall into eight clusters, six primarily informational, and one each of primarily transactional and navigational.

This study provides an important contribution to web search literature because it provides information about the goals of searchers and a method for automatically classifying the intents of the user queries. Automatic classification of user intent can lead to improved web search engines by tailoring results to specific user needs.

The paper discusses how web search engines can use automatically classified user queries to provide more targeted and relevant results in web searching by implementing a real time classification method as presented in this research.

This research investigates a new application of a method for automatically classifying the intent of user queries. There has been limited research to date on automatically classifying the user intent of web queries, even though the pay‐off for web search engines can be quite beneficial.

Examines the use of query reformulation, and particularly the use of relevance feedback by users of the Excite Web search engine. A total of 985 user search sessions from a data set of 18,113 user search sessions containing 51,473 queries were examined. Includes a qualitative and quantitative analysis of 191 user sessions including more than one query, to examine patterns of user query reformulation; and second, all 804 user sessions including relevance feedback were examined. Results show limited use of query reformulation and relevance feedback by Excite users – only one in five users reformulated queries. Most relevance feedback sessions were successful. Identifies the most common pattern of searching and discusses implications for Web search system design.

This research is based on the premise that current metrics for search engine advertising (SEA) are misleading and do not sufficiently allow managers to evaluate traffic and conversions simultaneously. This study aimed to conceptually develop and assess conversion potential (CvP) as a unifying construct for both measuring and evaluating the performance of SEA campaigns.

A data set of nearly seven million records covering almost three years of a multi-million-dollar keyword marketing campaign from a major US retailer was used to validate the construct of CvP.

Results empirically validate how CvP measures both campaign traffic and sales in SEA, using the optimization factor of ad rank, which is one of many possible factors.

Although the data set is large and covers a lengthy period of time, it is limited to one company in the retail sector.

The research instantiates CvP as a metric for overall SEA account performance while demonstrating that it is a practical tool for future campaign planning. The metric simultaneously incorporates a sales ratio and a traffic ratio.

This is the first study to formalize and provide a working definition of CvP in the academic literature. The contribution is a theoretical and practical managerial framework to mutually evaluate, measure and make decisions about SEA efforts.

User-generated social media comments can be a useful source of information for understanding online corporate reputation. However, the manual classification of these comments is challenging due to their high volume and unstructured nature. The purpose of this paper is to develop a classification framework and machine learning model to overcome these limitations.

The authors create a multi-dimensional classification framework for the online corporate reputation that includes six main dimensions synthesized from prior literature: quality, reliability, responsibility, successfulness, pleasantness and innovativeness. To evaluate the classification framework’s performance on real data, the authors retrieve 19,991 social media comments about two Finnish banks and use a convolutional neural network (CNN) to classify automatically the comments based on manually annotated training data.

After parameter optimization, the neural network achieves an accuracy between 52.7 and 65.2 percent on real-world data, which is reasonable given the high number of classes. The findings also indicate that prior work has not captured all the facets of online corporate reputation.

For practical purposes, the authors provide a comprehensive classification framework for online corporate reputation, which companies and organizations operating in various domains can use. Moreover, the authors demonstrate that using a limited amount of training data can yield a satisfactory multiclass classifier when using CNN.

This is the first attempt at automatically classifying online corporate reputation using an online-specific classification framework.

The purpose of this research is to show that federated content collections are important for providing access to multiple content repositories, including image, video, audio and Web sites.

This paper presents findings from an analysis of differences in users' Web searching patterns as they access various federated content collections. A dataset of 4,056,374 records submitted to the Dogpile.com Web meta‐search engine were analysed. An analysis was conducted of search session length, query length, number of results pages viewed, use of systems' assistance and the frequency of repeat queries.

Overall, users entered two to three terms per query and examined only the first pages of results. However, findings include differences in users' access patterns to various content collections. Web, news and audio queries were longer sessions but shorter queries. More users seeking images and videos sought systems assistance.

This is a large‐scale original study using data from a commercial Web search engine. The paper provides a valuable comparison of different types of search – text v. audio, image, etc.

The web is now a significant component of the recruitment and job search process. However, very little is known about how companies and job seekers use the web, and the ultimate effectiveness of this process. The specific research questions guiding this study are: how do people search for job‐related information on the web? How effective are these searches? And how likely are job seekers to find an appropriate job posting or application?

The data used to examine these questions come from job seekers submitting job‐related queries to a major web search engine at three points in time over a five‐year period.

Results indicate that individuals seeking job information generally submit only one query with several terms and over 45 percent of job‐seeking queries contain a specific location reference. Of the documents retrieved, findings suggest that only 52 percent are relevant and only 40 percent of job‐specific searches retrieve job postings.

This study provides an important contribution to web research and online recruiting literature. The data come from actual web searches, providing a realistic glimpse into how job seekers are actually using the web.

The results of this research can assist organizations in seeking to use the web as part of their recruiting efforts, in designing corporate recruiting web sites, and in developing web systems to support job seeking and recruiting.

This research is one of the first studies to investigate job searching on the web using longitudinal real world data.