Given the potential for technology to inflict harm and injustice on society, it is imperative that we cultivate a sense of social responsibility among our students as they progress through the Computer Science (CS) curriculum. Our students need to be able to examine the social complexities in which technology development and use are situated. Also, aligning students' personal goals and their ability to achieve them in their field of study is important for promoting motivation and a sense of belonging. Promoting communal goals while learning computing can help broaden participation, particularly among groups who have been historically marginalized in computing. Keeping these considerations in mind, we piloted an introductory Java programming course in which activities engaging students in ethical and socially responsible considerations were integrated across modules. Rather than adding social on top of the technical content, our curricular approach seeks to weave them together. The data from the class suggests that the students found the inclusion of the social context in the technical assignments to be more motivating and expressed greater agency in realizing social change. We share our approach to designing this new introductory socially responsible computing course and the students' reflections. We also highlight seven considerations for educators seeking to incorporate socially responsible computing.

We present a new high-quality validated image caption rating (VICR) dataset. How well a caption fits an image can be difficult to assess due to the subjective nature of caption quality. How do we evaluate whether a caption is good? We generated a new dataset to help answer this question by using our new image caption rating system, which consists of a novel robust rating scale and gamified approach to gathering human ratings. We show that our approach is consistent and teachable. 113 participants were involved in generating the dataset, which is composed of 68,217 ratings among 15,646 image-caption pairs. Our new dataset has greater inter-rater agreement than the state of the art, and custom machine learning rating predictors that were trained on our dataset outperform previous metrics. We improve over Flickr8k-Expert in Kendall's $W$ by 12\% and in Fleiss' $\kappa$ by 19\%, and thus provide a new benchmark dataset for image caption rating.

Science students increasingly need programming and data science skills to be competitive in the modern workforce. However, at our university (San Francisco State University), until recently, almost no biology, biochemistry, and chemistry students (from here bio/chem students) completed a minor in computer science. To change this, a new minor in computing applications, which is informally known as the Promoting Inclusivity in Computing (PINC) minor, was established in 2016. Here, we present the lessons we learned from our experience in a set of 10 rules. The first 3 rules focus on setting up the program so that it interests students in biology, chemistry, and biochemistry. Rules 4 through 8 focus on how the classes of the program are taught to make them interesting for our students and to provide the students with the support they need. The last 2 rules are about what happens "behind the scenes" of running a program with many people from several departments involved.

This paper presents Koob, an eBook Reader app that coalesces three key ideas to enhance students’ language learning, specifically for ambiguous words. The first idea is to improve the effectiveness of word lookup functionality through contextualization – by incorporating word sense disambiguation (WSD) techniques to show the contextually relevant definition at the top. The second idea is to augment WSD results with crowd-sourcing solutions. The last idea seeks to reinforce students’ learning by augmenting textual information with a visual aid, pictures related to the word, as part of the word lookup functionality. An empirical evaluation demonstrates that existing WSD techniques can successfully employed to dynamically reorder definitions such that the most relevant definition is at the top of the list for more than 80% of the instances.

This qualitative analysis explores the development of Computer Science (CS) identity of university students majoring in CS and students participating in a novel CS minor geared toward students who have traditionally been underrepresented in the field. We examine student perceptions of their CS identity at two critical junctures: pre-CS exposure (initial interest in CS), and during early CS exposure (performance and competence). Findings demonstrate the different paths to CS identity that the groups take, and highlight the importance of the CS educational environment in efforts to diversify the field.

BACKGROUND: Understanding the relationships between genes, drugs, and disease states is at the core of pharmacogenomics. Two leading approaches for identifying these relationships in medical literature are: human expert led manual curation efforts, and modern data mining based automated approaches. The former generates small amounts of high-quality data, and the latter offers large volumes of mixed quality data. The algorithmically extracted relationships are often accompanied by supporting evidence, such as, confidence scores, source articles, and surrounding contexts (excerpts) from the articles, that can be used as data quality indicators. Tools that can leverage these quality indicators to help the user gain access to larger and high-quality data are needed. APPROACH: We introduce GeneDive, a web application for pharmacogenomics researchers and precision medicine practitioners that makes gene, disease, and drug interactions data easily accessible and usable. GeneDive is designed to meet three key objectives: (1) provide functionality to manage information-overload problem and facilitate easy assimilation of supporting evidence, (2) support longitudinal and exploratory research investigations, and (3) offer integration of user-provided interactions data without requiring data sharing. RESULTS: GeneDive offers multiple search modalities, visualizations, and other features that guide the user efficiently to the information of their interest. To facilitate exploratory research, GeneDive makes the supporting evidence and context for each interaction readily available and allows the data quality threshold to be controlled by the user as per their risk tolerance level. The interactive search-visualization loop enables relationship discoveries between diseases, genes, and drugs that might not be explicitly described in literature but are emergent from the source medical corpus and deductive reasoning. The ability to utilize user's data either in combination with the GeneDive native datasets or in isolation promotes richer data-driven exploration and discovery. These functionalities along with GeneDive's applicability for precision medicine, bringing the knowledge contained in biomedical literature to bear on particular clinical situations and improving patient care, are illustrated through detailed use cases. CONCLUSION: GeneDive is a comprehensive, broad-use biological interactions browser. The GeneDive application and information about its underlying system architecture are available at http://www.genedive.net. GeneDive Docker image is also available for download at this URL, allowing users to (1) import their own interaction data securely and privately; and (2) generate and test hypotheses across their own and other datasets.

Alma project focuses on retention of Historically Underrepresented (HU) students in STEM fields by affirming their cultural capitals (skills, knowledge, communities, and abilities that students possess). Students are asked to write reflective journals on prompts such as `Why am I here?' to reminds them of their cultural capitals, and career aspirations. These essays are then analyzed by the Alma team to identify mentions of cultural capital themes (CCT) such as Attainment (describes a tangible goal), or First Generation (identifies student being first in family to attend college). However, detecting these CCTs in student essays is a labor intensive task. Our work offers a computational solution that is scalable and effective for this problem. We propose TACCTI (pronounced as Tacit), Text analysis and mAchine learning for Cultural Capital Theme Identification - a computational framework that employs latest developments in natural language processing and machine learning to identify instances of cultural capital themes in student essays. An empirical evaluation using Logistic Regression, Random Forest, LSTM, and BERT algorithms for the task of detecting presence (or absence) of Attainment CCT provides F1 scores of 0.82, 0.81, 0.84, and 0.92, respectively. Classification models for detecting First Generation CCT demonstrate that when limited training data is available, the traditional classification algorithms outperform deep learning based approaches - Logistic Regression and BERT models offer effectiveness of 0.91 and 0.83, respectively. Additional analysis demonstrates that word embeddings and named entity type of features (signals) have the highest influence on the performance of the classification models.

Underrepresentation of women and Black and Latinx individuals in computer science (CS) is a well-documented issue facing university training programs and the field in general. In an effort to expand on current knowledge and help bridge the equality gap in CS, a pilot interdisciplinary Computing Applications minor program was started in 2016 at San Francisco State University (SFSU). The "Promoting INclusivity in Computing" (PINC) program was designed to improve diversity in computing and increase computing literacy in data-intensive fields, specifically biology and chemistry. Students participating in the PINC program were compared to lower division CS majors at SFSU on measures assessing their attitudes toward computer science, goal-setting tendencies, experience of stereotype threat, general self-efficacy, and computer science self-efficacy. Analysis showed that students in the PINC program reported lower levels of computer science self-efficacy, but there were no significant differences between groups on self-report measures of goal-setting tendencies, experience of stereotype threat, attitudes toward computer science, and general self-efficacy. These findings highlight the success of the minor program in creating an educational environment that supports the achievement of underrepresented (UR) students, as well as the similar psychoeducational traits of the two groups of students. Findings may be of particular interest to postsecondary CS teachers, researchers interested in social justice and representation issues as they pertain to the field of computing, and university and departmental administrators who wish to increase and promote diversity in their CS programs.

We present our attempt at developing an efficient Question Answering system for both factoid and non-factoid questions from any domain. Empirical evaluation of our system using multiple datasets demonstrates that our system outperforms the best system from the TREC LiveQA tracks, while keeping the response time to under less than half a minute.

In this paper we present a pilot program at San Francisco State University, Promoting INclusivity in Computing (PINC), that is designed to achieve two goals simultaneously: (i) improving diversity in computing, and (ii) increasing computing literacy in data-intensive fields. To achieve these goals, the PINC program enrolls undergraduate students from non Computer Science (non-CS) fields, such as, Biology, that have become increasingly data-driven, and that traditionally attract diverse student population. PINC incorporates several well-established pedagogical practices, such as, cohort-based program structure, near-peer mentoring, and project-driven learning, to attract, retain, and successfully graduate a highly diverse and interdisciplinary student body. On successful completion of the program, students are awarded a minor in Computing Applications. Since its inception 18 months ago, 60 students have participated in this program. Of these 73% are women, and 51% are underrepresented minorities (URM). 74% of the participating students had nominal or no exposure to computer programming before PINC. Findings from student surveys show that majority of the PINC students now feel less intimidated about computer programming, and vividly see its utility and necessity. For several students, participation in the PINC program has already opened up career pathways (industry and academic summer internships) that were not available to them before.

Rich and comprehensive knowledge graphs (KG) of the Web, such as, Google KG, NELL, and Diffbot KG, are becoming increasingly prevalent and powerful as the underlying AI technology is rapidly progressing. In this work, we leverage this ongoing advancement for the task of answering questions posed from any domain and any type (factoid and non-factoid). We present a framework for knowledge graph based question answering systems, KGQA, and experiment with an instance of this framework that employs Diffbot KG. The unique features offered by KGs, such as, rapid query response time, connections between related graph objects, and structured information, are used to design a QA system that is effective and efficient.

The traditional search solution for large collections divides the collection into subsets ( shards ), and processes the query against all shards in parallel ( exhaustive search ). The search cost and the computational requirements of this approach are often prohibitively high for organizations with few computational resources. This article investigates and extends an alternative: selective search , an approach that partitions the dataset based on document similarity to obtain topic-based shards , and searches only a few shards that are estimated to contain relevant documents for the query. We propose shard creation techniques that are scalable, efficient, self-reliant, and create topic-based shards with low variance in size, and high density of relevant documents. The experimental results demonstrate that the effectiveness of selective search is on par with that of exhaustive search, and the corresponding search costs are substantially lower with the former. Also, the majority of the queries perform as well or better with selective search. An oracle experiment that uses optimal shard ranking for a query indicates that selective search can outperform the effectiveness of exhaustive search. Comparison with a query optimization technique shows higher improvements in efficiency with selective search. The overall best efficiency is achieved when the two techniques are combined in an optimized selective search approach.

Large document collections can be partitioned into 'topical shards' to facilitate distributed search. In a low-resource search environment only a few of the shards can be searched in parallel. Such a search environment faces two intertwined challenges. First, determining which shards to consult for a given query: shard ranking. Second, how many shards to consult from the ranking: cutoff estimation. In this paper we present a family of three algorithms that address both of these problems. As a basis we employ a commonly used data structure, the central sample index (CSI), to represent the shard contents. Running a query against the CSI yields a flat document ranking that each of our algorithms transforms into a tree structure. A bottom up traversal of the tree is used to infer a ranking of shards and also to estimate a stopping point in this ranking that yields cost-effective selective distributed search. As compared to a state-of-the-art shard ranking approach the proposed algorithms provide substantially higher search efficiency while providing comparable search effectiveness.

Content on the Internet is always changing. We explore the value of biasing search result snippets towards new webpage content. We present results from a user study comparing traditional query-focused snippets with snippets that emphasize new page content for two query types: general and trending. Our results indicate that searchers prefer the inclusion of temporal information for trending queries but not for general queries, and that this is particularly valuable for pages that have not been recently crawled.

Web search is strongly influenced by time. The queries people issue change over time, with some queries occasionally spiking in popularity (e.g., earthquake) and others remaining relatively constant (e.g., youtube). The documents indexed by the search engine also change, with some documents always being about a particular query (e.g., the Wikipedia page on earthquakes is about the query earthquake) and others being about the query only at a particular point in time (e.g., the New York Times is only about earthquakes following a major seismic activity). The relationship between documents and queries can also change as people's intent changes (e.g., people sought different content for the query earthquake before the Haitian earthquake than they did after). In this paper, we explore how queries, their associated documents, and the query intent change over the course of 10 weeks by analyzing query log data, a daily Web crawl, and periodic human relevance judgments. We identify several interesting features by which changes to query popularity can be classified, and show that presence of these features, when accompanied by changes in result content, can be a good indicator of change in query intent.

Indexes for large collections are often divided into shards that are distributed across multiple computers and searched in parallel to provide rapid interactive search. Typically, all index shards are searched for each query. For organizations with modest computational resources the high query processing cost incurred in this exhaustive search setup can be a deterrent to working with large collections. This paper investigates document allocation policies that permit searching only a few shards for each query (selective search) without sacrificing search accuracy. Random, source-based and topic-based document-to-shard allocation policies are studied in the context of selective search.