Web search is increasingly used to satisfy complex, exploratory information goals. Exploring and synthesizing information into knowledge can be slow and cognitively demanding due to a disconnect between search tools and sense-making workspaces. Our work explores how we might integrate contextual query suggestions within a person's sensemaking environment. We developed InterWeave a prototype that leverages a human wizard to generate contextual search guidance and to place the suggestions within the emergent structure of a searchers’ notes. To investigate how weaving suggestions into the sensemaking workspace affects a user's search and sensemaking behavior, we ran a between-subjects study (n=34) where we compare InterWeave’s in context placement with a conventional list of query suggestions. InterWeave’s approach not only promoted active searching, information gathering and knowledge discovery, but also helped participants keep track of new suggestions and connect newly discovered information to existing knowledge, in comparison to presenting suggestions as a separate list. These results point to directions for future work to interweave contextual and natural search guidance into everyday work.
Reviewing the literature to understand relevant threads of past work is a critical part of research and vehicle for learning. However, as the scientific literature grows the challenges for users to find and make sense of the many different threads of research grow as well. Previous work has helped scholars to find and group papers with citation information or textual similarity using standalone tools or overview visualizations. Instead, in this work we explore a tool integrated into users' reading process that helps them with leveraging authors' existing summarization of threads, typically in introduction or related work sections, in order to situate their own work's contributions. To explore this we developed a prototype that supports efficient extraction and organization of threads along with supporting evidence as scientists read research articles. The system then recommends further relevant articles based on user-created threads. We evaluate the system in a lab study and find that it helps scientists to follow and curate research threads without breaking out of their flow of reading, collect relevant papers and clips, and discover interesting new articles to further grow threads.
Personal cloud storage systems increasingly offer recommendations to help users retrieve or manage files of interest. For example, Google Drive's Quick Access predicts and surfaces files likely to be accessed. However, when multiple, related recommendations are made, interfaces typically present recommended files and any accompanying explanations individually, burdening users. To improve the usability of ML-driven personal information management systems, we propose a new method for summarizing related file-management recommendations. We generate succinct summaries of groups of related files being recommended. Summaries reference the files' shared characteristics. Through a within-subjects online study in which participants received recommendations for groups of files in their own Google Drive, we compare our summaries to baselines like visualizing a decision tree model or simply listing the files in a group. Compared to the baselines, participants expressed greater understanding and confidence in accepting recommendations when shown our novel recommendation summaries.
Modern knowledge workers typically need to use multiple resources, such as documents, web pages, and applications, at the same time. This complexity in their computing environments forces workers to restore various resources in the course of their work. However, conventional curation methods like bookmarks, recent document histories, and file systems place limitations on effective retrieval. Such features typically work only for resources of one type within one application, ignoring the interdependency between resources needed for a single task. In addition, text-based handles do not provide rich cues for users to recognize their associated resources. Hence, the need to locate and reopen relevant resources can significantly hinder knowledge workers' productivity. To address these issues, we designed and developed Scrapbook, a novel application for digital resource curation across applications that uses screenshot-based bookmarks. Scrapbook extracts and stores all the metadata (URL, file location, and application name) of windows visible in a captured screenshot to facilitate restoring them later. A week-long field study indicated that screenshot-based bookmarks helped participants curate digital resources. Additionally, participants reported that multimodal---visual and textual---data helped them recall past computer activities and reconstruct working contexts efficiently.
The vast scale and open-ended nature of knowledge graphs (KGs) make exploratory search over them cognitively demanding for users. We introduce a new technique, polymorphic lenses, that improves exploratory search over a KG by obtaining new leverage from the existing preference models that KG-based systems maintain for recommending content. The approach is based on a simple but powerful observation: in a KG, preference models can be re-targeted to recommend not only entities of a single base entity type (e.g., papers in the scientific literature KG, products in an e-commerce KG), but also all other types (e.g., authors, conferences, institutions; sellers, buyers). We implement our technique in a novel system, FeedLens, which is built over Semantic Scholar, a production system for navigating the scientific literature KG. FeedLens reuses the existing preference models on Semantic Scholar---people's curated research feeds---as lenses for exploratory search. Semantic Scholar users can curate multiple feeds/lenses for different topics of interest, e.g., one for human-centered AI and another for document embeddings. Although these lenses are defined in terms of papers, FeedLens re-purposes them to also guide search over authors, institutions, venues, etc. Our system design is based on feedback from intended users via two pilot surveys (n=17 and n=13, respectively). We compare FeedLens and Semantic Scholar via a third (within-subjects) user study (n=15) and find that FeedLens increases user engagement while reducing the cognitive effort required to complete a short literature review task. Our qualitative results also highlight people's preference for this more effective exploratory search experience enabled by FeedLens.
We propose a text editor to help users plan, structure and reflect on their writing process. It provides continuously updated paragraph-wise summaries as margin annotations, using automatic text summarization. Summary levels range from full text, to selected (central) sentences, down to a collection of keywords. To understand how users interact with this system during writing, we conducted two user studies (N=4 and N=8) in which people wrote analytic essays about a given topic and article. As a key finding, the summaries gave users an external perspective on their writing and helped them to revise the content and scope of their drafted paragraphs. People further used the tool to quickly gain an overview of the text and developed strategies to integrate insights from the automated summaries. More broadly, this work explores and highlights the value of designing AI tools for writers, with Natural Language Processing (NLP) capabilities that go beyond direct text generation and correction.