tocauthor: Jansen_B* : Human-Computer Interaction Bibliography Search

An Analysis of Cognitive Learning Context in MOOC Forum Messages Late-Breaking Works: Collaborative Technologies / Wong, Jian-Syuan / Pursel, Bart / Divinsky, Anna / Jansen, Bernard J. Extended Abstracts of the ACM CHI'16 Conference on Human Factors in Computing Systems 2016-05-07 v.2 p.1315-1321

ACM Digital Library Link

Summary: In this research, we analyze a large number of discussions of forum messages from three MOOC courses using a keyword taxonomy approach to identify learning processes occurring among the students. We conduct analysis on more than 100,000 forum messages from 14,647 forum threads from three MOOCs, with a combined 200,000+ enrollment. We map messages to six levels of Bloom's Taxonomy for cognitive learning. The results of this research indicate that learning processes of particular cognitive learning levels could be observed within discussions on MOOC forums. Results imply that different types of forum communications have features associated to particular learning levels, and the volume of higher levels of cognitive learning domains increase as the course progresses.

Shop Together, Search Together: Collaborative E-commerce Late-Breaking Works: Interaction in Specific Domains / Gao, Yanjun / Reddy, Madhu / Jansen, Bernard J. Extended Abstracts of the ACM CHI'16 Conference on Human Factors in Computing Systems 2016-05-07 v.2 p.2081-2087

ACM Digital Library Link

Summary: We present research on the development of a collaborative searching system for ecommerce shopping, based on domain specific requirements of retail shopping. We describe the design rationale for the system development and inclusion of collaborative search features, including search, chat, clipboard, product suggestions, shared views, and shopping cart. Our research goal is to understand whether collaborative searching tools are useful in supporting actual collaborative shopping tasks. In addition to describing the system development, we report findings from some preliminary user study. The findings highlight that collaborative search systems for domain specific areas such as online shopping can support collaborative searching, shared views, and group communication to aid in the completion of collaborative tasks.

A Taxonomy for Classifying Questions Asked in Social Question and Answering WIP Theme: Social Computing / Liu, Zhe / Jansen, Bernard J. Extended Abstracts of the ACM CHI'15 Conference on Human Factors in Computing Systems 2015-04-18 v.2 p.1947-1952

ACM Digital Library Link

Summary: The rapid advancement of Web2.0 technologies has made social networking sites, such as Facebook and twitter, important venues for individuals to seek and share information. As understanding the information needs of users is crucial for designing and developing tools to support their social Q&A behaviors, in this paper, we present a new way of classifying questions from a design perspective, with the aim of facilitating the development of question routing systems according to individual's information need. As an attempt to understand the questioner's intent in social question and answering environments, we propose a taxonomy of questions posted on Twitter, called ASK. Our taxonomy uncovers three different kinds of questions: accuracy, social, and knowledge. In addition, to enable automatic detection on these three types of information needs, we measured and reported on the differences in ASK types of questions reflected at both lexical and syntactic levels.

Linking external and internal search: investigating the site searching patterns of referred searchers Works-in-progress / Ortiz-Cordova, Adan / Jansen, Bernard J. Proceedings of ACM CHI 2014 Conference on Human Factors in Computing Systems 2014-04-26 v.2 p.1345-1350

ACM Digital Library Link

Summary: In this research, we investigate the relationship between external search on a major search engine and the subsequent internal search on an individual web site. Insights in the relationship can be a competitive advantage for websites. We use 295,271 searching sessions of an online Spanish entertainment business collected over a five month period. We develop a classification scheme for external and internal search queries using the referral query as the starting point. Using an n-gram approach, we identify query patterns for 295,271 searching episodes. We aggregate and identify six searching patterns. The three major searching strategies are Explorers (47%, a broad query for external search and then multiple broad queries during internal search), Navigators (16%, a navigational query for external search and then specific queries during internal search), and Acquirers (15%, transaction queries for both external and internal search). The remaining three patterns are Shifters (12%), Persisters (7%), and Orienteers (3%). Identification of searching patterns and related content can be a competitive advantage for websites dependent on providing relevant, fresh, and locatable information.

Predicting potential responders in social Q&A based on non-QA features Works-in-progress / Liu, Zhe / Jansen, Bernard J. Proceedings of ACM CHI 2014 Conference on Human Factors in Computing Systems 2014-04-26 v.2 p.2131-2136

ACM Digital Library Link

Summary: Given the recent advancement of online social networking technologies, social question and answering has become an important venue for individuals to seek and share information. While studies have suggested the possibilities of routing questions to potential answerers for their help and the information provided, there is little analysis proposed to identify the characteristics that differentiate the possible responders from the nonresponders. In order to address such gap, in this work we present a model to predict potential responders in social Q&A using only non-QA-based attributes. We build the classifier using features from two different aspects, including: features extracted from one's social profile and style of posting. To evaluate our model, we collect over 20,000 questions posted on Wenwo, a social Q&A application based on Weibo, along with all their responders. Our experimental results over the collected dataset demonstrate the effectiveness of responder prediction based on non-QA features and proposed potential implications for system design.

Understanding the specificity of web search queries Web and ecommerce / Hafernik, Carolyn Theresa / Jansen, Bernard J. Extended Abstracts of ACM CHI'13 Conference on Human Factors in Computing Systems 2013-04-27 v.2 p.1827-1832

ACM Digital Library Link

Summary: Understanding the specificity of Web search queries can help search systems better address the underlying needs of searchers and provide them relevant content. The goal of this work is to automatically determine the specificity of web search queries. Although many factors may impact the specificity of Web search queries, we investigate two factors of specificity in this research, (1) part of speech and (2) query length. We use content analysis and prior research to develop a list of nine attributes to identify query specificity. The attributes are whether a query contains a URL, a location or place name along with additional terms, compares multiple things, contains multiple distinct ideas or topics, a question that has a clear answer, request for directions, instructions or tips, a specific date and additional terms or a name and additional terms. We then apply these attributes to classify 5,115 unique queries as narrow or general. We then analyze the differences between narrow and general queries based on part of speech and query length. Our results indicate that query length and parts-of-speech usage, by themselves, can distinguish narrow and general queries. We discuss the implications of this work for search engines, marketers and users.

The gender-brand effect of key phrases on user clicks in sponsored search Web and ecommerce / Mukherjee, Partha / Jansen, Bernard J. Extended Abstracts of ACM CHI'13 Conference on Human Factors in Computing Systems 2013-04-27 v.2 p.1845-1850

ACM Digital Library Link

Summary: In this research, we analyze the relationship among (1) the numbers of clicks generated by the key-phrases users provide as queries in sponsored search, (2) the interaction between the gender orientation of those key-phrases, and (3) the occurrence of branded terms in those queries. The aim of this research is increased personalization of search engine results for branded queries targeting a specific gender. This will improve the consumer's online searching experience and potential interest in ads with branding focus. Increased personalization of search engine results and enhancement of users' interest in branded ads will also increase the revenue and profit of the advertisers. Our data consists of 7 million daily records from a keyword advertising campaign from a major US retailer. We segregate the key-phrases into six different categories. The gender orientation of terms has male, female and neutral categories each with two groups: -- branded and unbranded phrases. Using one way Analysis of Variance, we analyze the effect of gender orientation of both branded and unbranded key-phrases on number of users' clicks on the queries submitted to web search engine. The result shows that the means of users' clicks significantly vary among the categories. Moreover the result shows that the group formed by combination of female gender with branded terms generates maximum number of clicks among all six categories. Females may be more attracted to the use of branded terms due to the positive attitude and customer loyalty generated by brand image.

Factors influencing the response rate in social question and answering behavior Q&A / Liu, Zhe / Jansen, Bernard J. Proceedings of ACM CSCW'13 Conference on Computer-Supported Cooperative Work 2013-02-23 v.1 p.1263-1274

ACM Digital Library Link

Summary: With the increasing growth and popularity of social networking sites, social question and answering has become a venue for individuals to seek and share information. This study evaluates eleven extrinsic factors that may influence the response rate in social question and answering. These factors include the number of followers, the frequency of posting, the number of at-mentioned recipients, whether or not a question contains an at-mentioned verified account, unverified account, hashtag, emoticon, expression of gratitude, repeated punctuation or interjections, as well as the topic and the posting time of a question. We collected and analyzed over 10,000 questions from Sina Weibo. Eight out of all eleven features were found to significantly predict the number of responses received. We believe that our study is of significant value in providing insights for the design and development of future social question and answering tools, as well as enhancing the collaboration among social network users in supporting social information seeking activities.

Being networked and being engaged: the impact of social networking on ecommerce information behavior Social Media / Jansen, Bernard J. / Sobel, Kate / Cook, Geoff Proceedings of the 2011 iConference 2011-02-08 p.130-136

ACM Digital Library Link

Summary: Teenagers and young adults born between 1981 and 2000 are a critical demographic group economically and are one of the first demographics presented with an array of Internet social networking services just as their online habits are forming. Based on a survey of 34,514 teen and young adult respondents, the research reported in this paper is a descriptive and inferential analysis of reported ecommerce information behaviors on four social networking sites (Facebook, MySpace, myYearbook, and Twitter). We use k-means clustering analysis to find groups of these users based on their levels of being networked on and being engaged with social networking services. Results show that the majority of this demographic have accounts on multiple social networking sites and specific sites result in different information behaviors. More than 40% engage in three social networking sites and an additional 20% have four social networking accounts. We also found that there are distinct information behavioral differences among eight distinct clusters of users, indicating that companies may need to employ advanced analytical techniques to segment the youth market. We also investigate the motivations for using different social media sites. Findings show that this young demographic has complex ecommerce information behaviors that call for nuanced approaches in advertising, marketing, or other areas of information targeting.

The ubiquitous and increasingly significant status message Human interfaces / Jansen, Bernard J. / Chowdury, Abdur / Cook, Geoff interactions 2010-05 v.17 n.3 p.15-17

ACM Digital Library Link

Gen X and Ys attitudes on using social media platforms for opinion sharing Work-in-progress, April 14-15 / Jansen, Bernard J. / Sobel, Kate / Cook, Geoff Proceedings of ACM CHI 2010 Conference on Human Factors in Computing Systems 2010-04-10 v.2 p.3853-3858

Keywords: Facebook, MySpace, Twitter, information sharing, myYearbook, social media, social networking

ACM Digital Library Link

Summary: In this paper, we investigate opinion sharing attitudes and behaviors of 13-24 year olds on social media platforms. This research utilizes data from 34,514 survey respondents from users of the social media site, myYearbook. Results show that those more engaged with multiple social media platforms are more willing to share opinions, seek opinions, and act on these opinions. However, there were statistically significant differences among users of myYearbook, MySpace, Facebook, and Twitter. Findings show that the reported demographic differences and social network service chosen have an effect on behaviors. These results have implications for businesses and others interested in advertising on these platforms, and researchers interested in investigating these populations.

Real time search user behavior Work-in-progress, April 14-15 / Jansen, Bernard J. / Campbell, Gerry / Gregg, Matthew Proceedings of ACM CHI 2010 Conference on Human Factors in Computing Systems 2010-04-10 v.2 p.3961-3966

Keywords: collecta, real time content, real time search, twitter

ACM Digital Library Link

Summary: Real time search is an increasingly important area of information seeking on the Web. In this research, we analyze 1,005,296 user interactions with a real time search engine over a 190 day period. We investigate aggregate usage of the search engine, such as number of users, queries, and terms. We also investigate the structure of queries and terms submitted by these users. The results are compared to Web searching on traditional search engines. Results show that 60% of the traffic comes from the engine's application program interface, indicating that real time search is heavily leveraged by other applications. Of the queries, 30% were unique (used only once in the entire dataset). The most frequent query accounted for 0.003% of the query set. Less than 8% of the terms were unique. The most frequently used terms accounted for only 0.03% of the total terms. Concerning search topics, the most used terms dealt with technology, entertainment, and politics, reflecting both the temporal nature of the queries and, perhaps, an early adopter user-based. Sexual queries were quite low, relative to traditional Web search. Searchers of real time content often repeat queries overtime, perhaps indicating long term interest in a topic. We discuss the implications for search engines and information providers as real time content increasingly enters the main stream.

Classifying web queries by topic and user intent Work-in-progress, April 14-15 / Jansen, Bernard J. / Booth, Danielle Proceedings of ACM CHI 2010 Conference on Human Factors in Computing Systems 2010-04-10 v.2 p.4285-4290

Keywords: search engines, user intent, web queries, web searching

ACM Digital Library Link

Summary: In this research, we investigate a methodology to classify automatically Web queries by topic and user intent. Taking a 20,000 plus Web query data set sectioned by topic, we manually classified each query using a three-level hierarchy of user intent. We note that significant differences in user intent across topics. Results show that user intent (informational, navigational, and transactional) varies by topic (15 to 24 percent depending on the category). We then use this manually classified data set to classify searches in a Web search engine query stream automatically, using an exact match followed by n-gram approach. These approaches have the advantage of being implementable in real time for query classification of Web searches. The implications are that a search engine can improve retrieval performance by more effectively identifying the intent underlying user queries.

Gender demographic targeting in sponsored search User characteristics and large-scale tracking / Jansen, Bernard J. / Solomon, Lauren Proceedings of ACM CHI 2010 Conference on Human Factors in Computing Systems 2010-04-10 v.1 p.831-840

Keywords: gender, gender personalization, keyword advertising, pay-per-click, ppc, sponsored search, target audience description

ACM Digital Library Link

Summary: In this research, we evaluate the effect of gender in analyzing the performance of sponsored search advertising. We examine a log file with data comprised of nearly 7,000,000 records spanning 33 consecutive months of a search engine marketing campaign from a major US retailer. We classify key phrases selected for the campaign with a probability of being targeted for a specific gender and then compare the consumer actions using the critical sponsored search metrics of impressions, clicks, cost-per-click, sales revenue, orders, and items sold. Findings from our analysis show that the gender-orientation of the key phrase is a significant determinant in predicting behaviors and performance, with statistically different consumer behaviors for all attributes as the probability of a male or female keyword phrase changes. However, gender neutral phrases perform the best overall, calling into question the benefits of demographic targeting. Insight from this research could result in sponsored results being more effectively targeted to searchers and potential consumers.

System Controlled Assistance for Improving Search Performance Posters/Demos / Jansen, Bernard Proceedings of the Workshop on Human-Computer Interaction and Information Retrieval 2009-10-23 p.70-73

Summary: This position paper outlines the concept of system assistance as a method to improve searching performance. I present an investigation concerning the effects of user-controlled versus system-controlled assistance on searching performance using a within subjects, counterbalanced empirical evaluation. Forty-three subjects interacted with two fully functional, information retrieval systems offering searching assistance based on implicit feedback. The systems were identical in all respects except that one offered searching assistance via a help link, and the other offered system-controlled support at specified points during the search progress based on patterns of searcher interactions. The evaluation used the W2G Text REtrieval Conference document collection with six topics. Research results indicate that offering system-controlled assistance based on patterns of implicit feedback can improve searching performance based on user selected relevant documents, with an approximately 30% performance increase overall. I discuss the implications for the design of future searching systems with assistance that is based on user implicit feedback patterns.

Influences of mood on information seeking behavior Student research competition / Zhang, Mimi / Jansen, Bernard J. Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems 2009-04-04 v.2 p.3395-3400

Keywords: affect, emotion, information seeking behavior, mood, web search

ACM Digital Library Link

Summary: In this study, we explored how moods influence the way people seek information. We conducted a controlled lab study to test our hypotheses drawn from affect-as-information theory. Fifty-eight participants were randomly assigned to the happy or sad condition. They were primed for a certain mood, and they then performed a search task and finished a series of questionnaires. Our findings supported affect-as-information: the comparatively happy participants were inclined to process more general and less specific information; the comparatively sad participants were likely to process more specific information. The findings advances theoretical and empirical understanding concerning the characteristics of users' information seeking behavior under different moods. Our study will contribute to affective search systems design.

Micro-blogging as online word of mouth branding Spotlight on work in progress session 1 / Jansen, Bernard J. / Zhang, Mimi / Sobel, Kate / Chowdury, Abdur Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems 2009-04-04 v.2 p.3859-3864

Keywords: branding, micro-blogging, social networking, twittering

ACM Digital Library Link

Summary: In this paper, we report research results investigating micro-blogging as a form of online word of mouth branding. We analyzed 149,472 micro-blog postings containing branding comments, sentiments, and opinions. We investigated the overall structure of these micro-blog postings, types of expressions, and sentiment fluctuations. Of the branding micro-blogs, nearly 20 percent contained some expressions of branding sentiments. Of these tweets with sentiments, more than 50 percent were positive and 33 percent critical of the company or product. We discuss the implications for organizations in using micro-blogging as part of their overall marketing strategy and branding campaigns.

Predicting query reformulation during web searching Spotlight on work in progress session 1 / Jansen, Bernard J. / Booth, Danielle / Spink, Amanda Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems 2009-04-04 v.2 p.3907-3912

Keywords: n-grams, query reformulation, stochastic process, web queries, web sessions

ACM Digital Library Link

Summary: his paper reports results from a study in which we automatically classified the query reformulation patterns for 964,780 Web searching sessions (composed of 1,523,072 queries) in order to predict what the next query reformulation would be. We employed an n-gram modeling approach to describe the probability of searchers transitioning from one query reformulation state to another and predict their next state. We developed first, second, third, and fourth order models and evaluated each model for accuracy of prediction. Findings show that Reformulation and Assistance account for approximately 45 percent of all query reformulations. Searchers seem to seek system searching assistant early in the session or after a content change. The results of our evaluations show that the first and second order models provided the best predictability, between 28 and 40 percent overall, and higher than 70 percent for some patterns. Implications are that the n-gram approach can be used for improving searching systems and searching assistance in real time.

Viewing Searching Systems as Learning Systems Posters/Demos / Jansen, Bernard Proceedings of the Workshop on Human-Computer Interaction and Information Retrieval 2008-10-23 p.42-45

Summary: Investigating whether users of a searching system are engaged in a learning environment, the results of this research show that information searching is a cognitive learning process with unique searching characteristics specific to particular learning levels. In a laboratory experiment, we studied the searching characteristics of 72 participants engaged in 426 searching tasks. We developed the searching tasks according to Anderson and Krathwohl's categories of the cognitive learning domain. Research results indicate that applying and analyzing, the middle two of the six categories, generally take the most searching effort in terms of queries per session, topics searched per session, and total time searching. The lowest two learning categories, remembering and understanding, exhibit searching characteristics similar to the highest order learning categories of evaluating and creating. These results suggest that users applied simple searching expressions to support their higher level information needs. These findings points to the need for searching system features that engage the user in a learning process.

Investigating the relevance of sponsored results for web ecommerce queries Posters / Jansen, Bernard J. Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2007-07-23 p.857-858

ACM Digital Library Link

Summary: Are sponsored links, the primary business model for Web search engines, providing Web consumers with relevant results? This research addresses this issue by investigating the relevance of sponsored and non-sponsored links for ecommerce queries from the major search engines. The results show that average relevance ratings for sponsored and non-sponsored links are virtually the same, although the relevance ratings for sponsored links are statistically higher. We used 108 ecommerce queries and 8,256 retrieved links for these queries from three major Web search engines, Google, MSN, and Yahoo!. We present the implications for Web search engines and sponsored search as a long-term business model as well as a mechanism for finding relevant information for searchers.

Viewing online searching within a learning paradigm Posters / Jansen, Bernard J. / Smith, Brian / Booth, Danielle L. Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2007-07-23 p.859-860

ACM Digital Library Link

Summary: In this research, we investigate whether one can model online searching as a learning paradigm. We examined the searching characteristics of 41 participants engaged in 246 searching tasks. We classified the searching tasks according to Anderson and Krathwohl's Taxonomy, an updated version of Bloom's taxonomy. Anderson and Krathwohl is a six level categorization of cognitive learning. Research results show that Applying takes the most searching effort as measured by queries per session and specific topics searched per sessions. The categories of Remembering and Understanding, which are lower-order learning levels, exhibit searching characteristics similar to the higher order categories of Evaluating and Creating. It seems that searchers rely primarily on their internal knowledge and use searching primarily as fact checking and verification when engaged in Evaluating and Creating. Implications are that the commonly held notions of Web searchers having simple information goals may not be correct. We discuss the implications for Web searching, including designing interfaces to support exploration and alternate views.

Brand awareness and the evaluation of search results Search / Jansen, Bernard J. / Zhang, Mimi / Zhang, Ying Proceedings of the 2007 International Conference on the World Wide Web 2007-05-08 p.1139-1140

ACM Digital Library Link

Summary: We investigate the effect of search engine brand (i.e., the identifying name or logo that distinguishes a product from its competitors) on evaluation of system performance. This research is motivated by the large amount of search traffic directed to a handful of Web search engines, even though most are of equal technical quality with similar interfaces. We conducted a laboratory study with 32 participants to measure the effect of four search engine brands while controlling for the quality of search engine results. There was a 25% difference between the most highly rated search engine and the lowest using average relevance ratings, even though search engine results were identical in both content and presentation. Qualitative analysis suggests branding affects user views of popularity, trust and specialization. We discuss implications for search engine marketing and the design of search engine quality studies.

Determining the user intent of web search engine queries Search / Jansen, Bernard J. / Booth, Danielle L. / Spink, Amanda Proceedings of the 2007 International Conference on the World Wide Web 2007-05-08 p.1149-1150

ACM Digital Library Link

Summary: Determining the user intent of Web searches is a difficult problem due to the sparse data available concerning the searcher. In this paper, we examine a method to determine the user intent underlying Web search engine queries. We qualitatively analyze samples of queries from seven transaction logs from three different Web search engines containing more than five million queries. From this analysis, we identified characteristics of user queries based on three broad classifications of user intent. The classifications of informational, navigational, and transactional represent the type of content destination the searcher desired as expressed by their query. We implemented our classification algorithm and automatically classified a separate Web search engine transaction log of over a million queries submitted by several hundred thousand users. Our findings show that more than 80% of Web queries are informational in nature, with about 10% each being navigational and transactional. In order to validate the accuracy of our algorithm, we manually coded 400 queries and compared the classification to the results from our algorithm. This comparison showed that our automatic classification has an accuracy of 74%. Of the remaining 25% of the queries, the user intent is generally vague or multi-faceted, pointing to the need to for probabilistic classification. We illustrate how knowledge of searcher intent might be used to enhance future Web search engines.

Understanding web search via a learning paradigm Search / Jansen, Bernard J. / Smith, Brian / Booth, Danielle L. Proceedings of the 2007 International Conference on the World Wide Web 2007-05-08 p.1207-1208

ACM Digital Library Link

Summary: Investigating whether one can view Web searching as a learning process, we examined the searching characteristics of 41 participants engaged in 246 searching tasks. We classified the searching tasks according an updated version of Bloom's taxonomy, a six level categorization of cognitive learning. Results show that Applying takes the most searching effort as measured by queries per session and specific topics searched per sessions. The lower level categories of Remembering and Understanding exhibit searching characteristics similar to the higher order learning of Evaluating and Creating. It appears that searchers rely primarily on their internal knowledge for Evaluating and Creating, using searching primarily as fact checking and verification. Implications are that the commonly held notion that Web searchers have simple information needs may not be correct. We discuss the implications for Web searching, including designing interfaces to support exploration.

The comparative effectiveness of sponsored and nonsponsored links for Web e-commerce queries / Jansen, Bernard J. ACM Transactions on The Web 2007-05 v.1 n.1 p.3

ACM Digital Library Link

Summary: The predominant business model for Web search engines is sponsored search, which generates billions in yearly revenue. But are sponsored links providing online consumers with relevant choices for products and services? We address this and related issues by investigating the relevance of sponsored and nonsponsored links for e-commerce queries on the major search engines. The results show that average relevance ratings for sponsored and nonsponsored links are practically the same, although the relevance ratings for sponsored links are statistically higher. We used 108 ecommerce queries and 8,256 retrieved links for these queries from three major Web search engines: Yahoo!, Google, and MSN. In addition to relevance measures, we qualitatively analyzed the e-commerce queries, deriving five categorizations of underlying information needs. Product-specific queries are the most prevalent (48%). Title (62%) and summary (33%) are the primary basis for evaluating sponsored links with URL a distant third (2%). To gauge the effectiveness of sponsored search campaigns, we analyzed the sponsored links from various viewpoints. It appears that links from organizations with large sponsored search campaigns are more relevant than the average sponsored link. We discuss the implications for Web search engines and sponsored search as a long-term business model and as a mechanism for finding relevant information for searchers.