In Interactive Information Retrieval (IIR) experiments the user's gaze motion on web pages is often recorded with eye tracking. The data is used to analyze gaze behavior or to identify Areas of Interest (AOI) the user has looked at. So far, tools for analyzing eye tracking data have certain limitations in supporting the analysis of gaze behavior in IIR experiments. Experiments often consist of a huge number of different visited web pages. In existing analysis tools the data can only be analyzed in videos or images and AOIs for every single web page have to be specified by hand, in a very time consuming process. In this work, we propose the reading protocol software which breaks eye tracking data down to the textual level by considering the HTML structure of the web pages. This has a lot of advantages for the analyst. First and foremost, it can easily be identified on a large scale what has actually been viewed and read on the stimuli pages by the subjects. Second, the web page structure can be used to filter to AOIs. Third, gaze data of multiple users can be presented on the same page, and fourth, fixation times on text can be exported and further processed in other tools. We present the software, its validation, and example use cases with data from three existing IIR experiments.

According to the cognitive viewpoint of information retrieval (IR) research, a search task can be conceptualized as a sequence of information seeking intentions which both motivate and are influenced by search behaviors. While the behavioral effects of task features have been thoroughly discussed in a large body of literature, how different information seeking intentions in query segments serve as bridges between task and Web search behavior still remains unexplored. To develop a more comprehensive, multi-level (i.e., task level, intention level, and behavior level) understanding of Web search, the authors analyzed intention and search behavior data collected from 693 query segments generated by 40 participants in a controlled lab setting, seeking to answer two main research questions: 1) from task to intention : how do different task features affect users' information seeking intentions at different stages of a search session? 2) from intention to behavior : How is a user's search behavior associated with their information seeking intentions in the current and next query segments respectively? The results demonstrate that: 1) Task features significantly affected the frequency of occurrence of most of the information seeking intentions, and these effects gradually faded away as search sessions proceeded; 2) The presences of a variety of intentions in both current and subsequent query segments were connected with and detectable by different subsets of behavioral measures. This study contributes to the understanding of the connections between task, intentions in query segments, and search behavior, and thereby has implications for designing system affordances for supporting different intentions and search activities in various task stages and contexts.

As understanding of web search behavior grows, researchers rapidly develop new study designs to capture and understand search behavior. Researchers have restricted time in which to design a study, develop a collection tool, collect data, analyze it, and report new insights. In particular, sufficient time and development skills are often required to create a tool that meets the needs of any particular web search behavior study. Coagmento is a tool that is developed for facilitating many of the needs for designing and running a lab study, from executing a session flow to collecting log data. By streamlining the programming of unique parts for a specific study, Coagmento helps researchers tailor various parts of running a user study, lowering the barrier for designing and conducting lab study experiments. One-click interactions with a graphical user interface permit researchers to operate through a web-based administrative service to generate stages, search tasks, and questionnaires for their interactive information retrieval studies. In this demonstration, Coagmento provides a solution to increase efficiency in the production of laboratory experiments for web search behavior.

Interactive information retrieval (IIR) researchers often conduct laboratory studies to understand the relationship between people seeking information and information retrieval systems. They develop extensive data collection methods and tools create new understanding about the relationship between observable behaviors, searcher context, and underlying cognition, to better support people's information seeking. Yet aside from the problems of data size, realism, and demographics, laboratory studies are limited in the number and nature of phenomena they can study. Hence, data collected in laboratories contains different searcher populations and collects non-overlapping user and task characteristics. While research analyses and collection methods are isolated, how can we further IIR's mission of broad understanding? We approach this as a structure learning problem on incomplete data, determining the extent to which incomplete data can be used to predict user and task characteristics from interactions. In particular, we examine whether combining heterogeneous data sets is more effective than using a single data set alone in prediction. Our results indicate that adding external data significantly improves predictions of searcher characteristics, task characteristics, and behaviors, even when the data does not contain identical information about searchers.

When users are looking for information on the Web, they show different behavior for different task types, e.g., for fact finding vs. information gathering tasks. For example, related work in this area has investigated how this behavior can be measured and applied to distinguish between easy and difficult tasks. In this work, we look at the searcher's behavior in the domain of journalism for four different task types, and additionally, for two different topics in each task type. Search behavior is measured with a number of session variables and correlated to subjective measures such as task difficulty, task success and the usefulness of documents. We acknowledge prior results in this area that task difficulty is correlated to user effort and that easy and difficult tasks are distinguishable by session variables. However, in this work, we emphasize the role of the task topic - in and of itself - over parameters such as the search results and read content pages, dwell times, session variables and subjective measures such as task difficulty or task success. With this knowledge researchers should give more attention to the task topic as an important influence factor for user behavior.

We explore the gap between 1) statistically significant relationships between task and browsing behavior and 2) predicting task type from such behaviors. Previous literature has shown relationships between Web browsing behavior and person»s corresponding search task. We find statistically significant browser features for detecting task - comparing the features to previous literature - and apply this knowledge to task classification of search sessions. Even though significant features improve prediction over baselines, it is not by much. We suggest that a more subtle treatment of such features should go beyond statistical significance. In some cases, considering personal patterns may be required for effective prediction.

In this demo, we present Coagmento, a Web-based, open-source tool for information seeking projects that collects information for individuals and groups and helps facilitate collaborative information seeking. Coagmento has been used in information retrieval and human-computer interaction studies to investigate individual and group information seeking behaviors in a lab or a field setting. In this demo, we discuss what Coagmento is, its past uses in prior studies, and its present state. We also discuss current work in progress. With Coagmento recently passing its 10th anniversary, we discuss our intention to make it a tool that is easy to configure for a human information behavior researcher with little programming skill.

One of the emerging and important problems in Interactive Information Retrieval research is predicting search tasks. Given a searcher's behavior during a search session, can the searcher's task be predicted? Which aspects of the task can be predicted, and how quickly and how accurately can the prediction be made? Much past literature has examined relationships between browsing behavior and task type at a statistical level, and recent work is moving towards prediction. While one may think whole session measures are useful for prediction, recent findings on common measures have suggested the contrary. Can less of the session still be useful? We examine the opposite end: the first query. Using multiple data sets for comparison, our results suggest that first query measures can be at least as good as -- and sometimes better than -- whole session measures for certain task type predictions.

It has been shown that people attempt to accomplish a variety of intentions during the course of an information seeking session, and there is reason to believe that these different information seeking intentions can benefit from system support tailored to each such intention. We address the problem of predicting the presence of such intentions during an information seeking session, through analysis of observable user search behaviors. We present results of a study of 40 participants, each working on two different journalism tasks, which investigated how their search behaviors could indicate their intentions. Using 725 query-segments captured from this study, we demonstrate that information seeking intentions can be predicted with a simple classification model using a linear combination of search behavior features that can be logged with a browser plug-in.

Query recommendation predominantly relies on search logs to use existing queries for recommendation, typically calculating query similarity metrics or transition probabilities from the log. While effective, such recommendations are limited to the queries, words, and phrases in the log. They hence do not recommend potentially useful, entirely novel queries. Recent query recommendation methods have proposed generating queries on a topical or thematic level, though current approaches are limited to generating single words. We propose a hybrid method for constructing multi-word queries in this generative sense. It uses Latent Dirichlet Allocation to generate a topic for exploration and skip-gram modeling to generate queries from the topic. According to additional evaluation metrics we present, our model improves diversity and has some room for improving relevance, yet offers an interesting avenue for query recommendation.

We present a method for extracting the self-reported intentions of users engaged in an information seeking episode. We recruited participants to conduct search sessions and subsequently asked them to self-report their intentions. A total of 27 users participated in a lab study, during which they worked on two search tasks. After each search session, participants indicated their intentions during that session while viewing a video replay. Results indicate that the set of search intentions provided to participants was sufficient to account for intentions in four journalism-related information seeking tasks: a copy editing task, interview preparation task, relationships task, and story pitch task. The results also suggest regular patterns in intentions that can be exploited for identification of task type as well as potential applications to personalization and recommendation during a search episode.