AI enabled value-oriented collaborative learning: Centre for innovative education

Collaborative learning allows students to pool their knowledge, skills, and experiences to better understand and learn from one another. Two of the most fundamental features of collaborative learning are the grouping of students and the gaining of knowledge through social interactions with peers. The term “blended learning” refers to a new approach to education that combines conventional and contemporary learning models, in which students' interaction with and education from their digital devices does not totally replace their interaction and education from their traditional teachers. However, there are a number of obstacles that prevent educators from fully grasping blended learning models and putting them into practice. There have been a number of difficulties in implementing blended learning models due to the varying degrees to which they are accepted and used. In this article, we talked about collaborative learning data analysis since it helps teachers determine if their pedagogical approaches are working and where they may be strengthened. These results have the potential to contribute to a more comprehensive knowledge of (Artificial Intelligence in Education) AIED and its consequences for educational policies, educational AI design, and instructional design geared toward improving (The School Advisory Council) SAC in education.     

论职业信息在西藏高校毕业生就业中的应用

近年来高校毕业生就业率持续走低,就业难问题受到了全社会的关注.其成因有多种因素,而职业信息则是影响毕业生就业的主要因素之一.本文就以西藏高校毕业生为研究对象来分析职业信息在大学毕业生就业中的作用及应用.     

Connecting user and item perspectives in popularity debiasing for collaborative recommendation

Recommender systems learn from historical users’ feedback that is often non-uniformly distributed across items. As a consequence, these systems may end up suggesting popular items more than niche items progressively, even when the latter would be of interest for users. This can hamper several core qualities of the recommended lists (e.g., novelty, coverage, diversity), impacting on the future success of the underlying platform itself. In this paper, we formalize two novel metrics that quantify how much a recommender system equally treats items along the popularity tail. The first one encourages equal probability of being recommended across items, while the second one encourages true positive rates for items to be equal. We characterize the recommendations of representative algorithms by means of the proposed metrics, and we show that the item probability of being recommended and the item true positive rate are biased against the item popularity. To promote a more equal treatment of items along the popularity tail, we propose an in-processing approach aimed at minimizing the biased correlation between user-item relevance and item popularity. Extensive experiments show that, with small losses in accuracy, our popularity-mitigation approach leads to important gains in beyond-accuracy recommendation quality.     

Integration of user profiles: models and experiments in information retrieval

One difficult problem in information retrieval (IR) is the proper interpretation of user queries. It is extremely hard for users to express their information needs in a specific yet exhaustive way. In an effort to alleviate this problem, two theoretical models have been proposed to utilize user characteristics maintained in the form of a user profile. Although the idea of integrating user profiles into an IR system is intuitively appealing, and the models seem viable, no research to date has established a foundation for the roles of user profiles in such a system. Aiming at the investigation of the roles of user profiles, therefore, this study first identifies and extends various query/profile interaction models to provide a ground upon which the investigation can be undertaken. From a continuum of models characterized on the basis of interaction types, metrics, and parameters, nearly 400 models are chosen to investigate the “model space.” New measures are developed based on the notion of user satisfaction/frustration. In addition, three different criteria are used to guide users in making judgments on the quality of retrieved items. Analysis of the data obtained from the experiments shows that, for a wide variety of criteria and metrics, there are always some query/profile interaction models that outperform the query alone model. In addition, preferable characteristics for different criteria are identified in terms of interaction types, parameters, and metrics.     

Collaborative information seeking: The combined activity of information seeking and collaborative grounding

Since common ground is pivotal to collaboration, this paper proposes to define collaborative information seeking as the combined activity of information seeking and collaborative grounding. While information-seeking activities are necessary for collaborating actors to acquire new information, the activities involved in information seeking are often performed by varying subgroups of actors. Consequently, collaborative grounding is necessary to share information among collaborating actors and, thereby, establish and maintain the common ground necessary for their collaborative work. By focusing on the collaborative level, collaborative information seeking aims to avoid both individual reductionism and group reductionism, while at the same time recognizing that only some information and understanding need be shared.     

Meta-Circuit machine: Inferencing human collaborative relationships in heterogeneous information networks

Human collaborative relationship inference is a meaningful task for online social networks and is called link prediction in network science. Real-world networks contain multiple types of interacting components and can be modeled naturally as heterogeneous information networks (HINs). The current link prediction algorithms in HINs fail to effectively extract training samples from snapshots of HINs; moreover, they underutilise the differences between nodes and between meta-paths. Therefore, we propose a meta-circuit machine (MCM) that can learn and fuse node and meta-path features efficiently, and we use these features to inference the collaborative relationships in question-and-answer and bibliographic networks. We first utilise meta-circuit random walks to obtain training samples in which the basic idea is to perform biased meta-path random walks on the input and target network successively and then connect them. Then, a meta-circuit recurrent neural network (mcRNN) is designed for link prediction, which represents each node and meta-path by a dense vector and leverages an RNN to fuse the features of node sequences. Experiments on two real-world networks demonstrate the effectiveness of our framework. This study promotes the investigation of potential evolutionary mechanisms for collaborative relationships and offers practical guidance for designing more effective recommendation systems for online social networks.     

Countering user risk in information system development projects

User related issues have long been broadly discussed in the information system development (ISD) project research area. In this study, we focus on user risk and identify two risk countering approaches to demonstrate how to deal with user risk and its negative impact on ISD projects. We hypothesize that (1) user risk has a negative impact on project performance, (2) users’ bond with the project and the development team can help reduce user risk, and (3) developers’ task knowledge and vertical coordination can ease the negative impact of user risk and increase project performance. A quantitative approach with survey data collected from 240 practitioners confirmed our hypotheses. In addition, we interviewed seven developers and three user representatives to complete our understanding of this issue. Implications for academia and practitioners are discussed at the end of this paper. Suggestions for future research directions are also provided.     

On domain expertise-based roles in collaborative information retrieval

Collaborative information retrieval involves retrieval settings in which a group of users collaborates to satisfy the same underlying need. One core issue of collaborative IR models involves either supporting collaboration with adapted tools or developing IR models for a multiple-user context and providing a ranked list of documents adapted for each collaborator. In this paper, we introduce the first document-ranking model supporting collaboration between two users characterized by roles relying on different domain expertise levels. Specifically, we propose a two-step ranking model: we first compute a document-relevance score, taking into consideration domain expertise-based roles. We introduce specificity and novelty factors into language-model smoothing, and then we assign, via an Expectation–Maximization algorithm, documents to the best-suited collaborator. Our experiments employ a simulation-based framework of collaborative information retrieval and show the significant effectiveness of our model at different search levels.     

Breakdowns in collaborative information seeking: A study of the medication process

Collaborative information seeking is integral to many professional activities. In hospital work, the medication process encompasses continual seeking for information and collaborative grounding of information. This study investigates breakdowns in collaborative information seeking through analyses of the use of the electronic medication record adopted in a Danish healthcare region and of the reports of 5 years of medication incidents at Danish hospitals. The results show that breakdowns in collaborative information seeking is a major source of medication incidents, that most of these breakdowns are breakdowns in collaborative grounding rather than information seeking, that the medication incidents mainly concern breakdowns in the use of records as opposed to oral communication, that the breakdowns span multiple degrees of separation between clinicians, and that the electronic medication record has introduced risks of new kinds of breakdown in collaborative information seeking. In working to prevent and recover from breakdowns in the seeking and sharing of information a focus on collaborative information seeking will point toward collaborative, organizational, and systemic reasons for breakdown and areas for improvement, rather than toward individual error.     

Search history support for finding and using information: User interface design recommendations from a user study

Recording search histories, presenting them to the searcher, and building additional interface tools on them offer many opportunities for supporting user tasks in information seeking and use. This study investigated the use of search history information in legal information seeking. Qualitative methods were used to explore how attorneys and law librarians used their memory and external memory aids while searching for information and in transferring to information use. Based on the findings, interface design recommendations were made for information systems.     

Putting explainable AI in context: institutional explanations for medical AI

Ethics and Information Technology - This paper approaches the interaction of a health professional with an AI system for diagnostic purposes as a hybrid decision making process and conceptualizes...     

Reprint of: Capturing conversations in entrepreneurial ecosystems

This paper examines a novel and innovative methodological approach and dataset for measuring the complex relational dynamics underpinning entrepreneurial ecosystems (EEs). Existing measurement techniques have largely failed to yield sufficiently nuanced data or insights to inform robust policy recommendations within this research field. To rectify this situation, this paper sets out a novel approach to assessing the relational connectivity within EEs by capturing entrepreneurial "conversations". Drawing on real-time data extracted from an event-based social media platform, in combination with social network analysis and qualitative interview data, we provide an in-depth assessment of the relational connections within the city of Edinburgh at three analytical levels. Overall, the paper demonstrates that the analysis of conversations and conversational spaces is an important mechanism for exploring and mapping the relational connectivity within EEs. As well as producing novel empirical insights, this approach provides policy makers with vital strategic policy intelligence to help better inform public policy frameworks and associated interventions.     

How user innovations become commercial products: A theoretical investigation and case study

In this paper we model the pathways commonly traversed as user innovations are transformed into commercial products. First, one or more users recognize a new set of design possibilities and begin to innovate. They then join into communities, motivated by the increased efficiency of collective innovation. User-manufacturers then emerge, using high-variable/low-capital cost production methods. Finally, as user innovation slows, the market stabilizes enough for high-capital, low-variable cost manufacturing to enter. We test the model against the history of the rodeo kayak industry and find it supported. We discuss implications for “dominant design” theory and for innovation practice.     

An experiment in building profiles in information filtering: the role of context of user relevance feedback

An experiment was conducted to see how relevance feedback could be used to build and adjust profiles to improve the performance of filtering systems. Data was collected during the system interaction of 18 graduate students with SIFTER (Smart Information Filtering Technology for Electronic Resources), a filtering system that ranks incoming information based on users' profiles. The data set came from a collection of 6000 records concerning consumer health. In the first phase of the study, three different modes of profile acquisition were compared. The explicit mode allowed users to directly specify the profile; the implicit mode utilized relevance feedback to create and refine the profile; and the combined mode allowed users to initialize the profile and to continuously refine it using relevance feedback. Filtering performance, measured in terms of Normalized Precision, showed that the three approaches were significantly different (α=0.05 and p=0.012). The explicit mode of profile acquisition consistently produced superior results. Exclusive reliance on relevance feedback in the implicit mode resulted in inferior performance. The low performance obtained by the implicit acquisition mode motivated the second phase of the study, which aimed to clarify the role of context in relevance feedback judgments. An inductive content analysis of thinking aloud protocols showed dimensions that were highly situational, establishing the importance context plays in feedback relevance assessments. Results suggest the need for better representation of documents, profiles, and relevance feedback mechanisms that incorporate dimensions identified in this research.     

A model for understanding collaborative information behavior in context: A study of two healthcare teams

Collaborative information behavior is an essential aspect of organizational work; however, we have very limited understanding of this behavior. Most models of information behavior focus on the individual seeker of information. In this paper, we report the results from two empirical studies that investigate aspects of collaborative information behavior in organizational settings. From these studies, we found that collaborative information behavior differs from individual information behavior with respect to how individuals interact with each other, the complexity of the information need, and the role of information technology. There are specific triggers for transitioning from individual to collaborative information behavior, including lack of domain expertise. The information retrieval technologies used affect collaborative information behavior by acting as important supporting mechanisms. From these results and prior work, we develop a model of collaborative information behavior along the axes of participant behavior, situational elements, and contextual triggers. We also present characteristics of collaborative information system including search, chat, and sharing. We discuss implications for the design of collaborative information retrieval systems and directions for future work.     

Explicitly integrating MeSH thesaurus help into health information retrieval systems: An empirical user study

When consumers search for health information, a major obstacle is their unfamiliarity with the medical terminology. Even though medical thesauri such as the Medical Subject Headings (MeSH) and related tools (e.g., the MeSH Browser) were created to help consumers find medical term definitions, the lack of direct and explicit integration of these help tools into a health retrieval system prevented them from effectively achieving their objectives. To explore this issue, we conducted an empirical study with two systems: One is a simple interface system supporting query-based searching; the other is an augmented system with two new components supporting MeSH term searching and MeSH tree browsing. A total of 45 subjects were recruited to participate in the study. The results indicated that the augmented system is more effective than the simple system in terms of improving user-perceived topic familiarity and question–answer performance, even though we did not find users spend more time on the augmented system. The two new MeSH help components played a critical role in participants’ health information retrieval and were found to allow them to develop new search strategies. The findings of the study enhanced our understanding of consumers’ search behaviors and shed light on the design of future health information retrieval systems.     

Beyond actions: Exploring the discovery of tactics from user logs

Search log analysis has become a common practice to gain insights into user search behaviour: it helps gain an understanding of user needs and preferences, as well as an insight into how well a system supports such needs. Currently, log analysis is typically focused on low-level user actions, i.e. logged events such as issued queries and clicked results, and often only a selection of such events are logged and analysed. However, types of logged events may differ widely from interface to interface, making comparison between systems difficult. Further, the interpretation of the meaning of and subsequent analysis of a selection of events may lead to conclusions out of context— e.g. the statistics of observed query reformulations may be influenced by the existence of a relevance feedback component. Alternatively, in lab studies user activities can be analysed at a higher level, such as search tactics and strategies, abstracted away from detailed interface implementation. Unfortunately, until now the required manual codings that map logged events to higher-level interpretations have prevented large-scale use of this type of analysis. In this paper, we propose a new method for analysing search logs by (semi-)automatically identifying user search tactics from logged events, allowing large-scale analysis that is comparable across search systems. In addition, as the resulting analysis is at a tactical level we reduce potential issues surrounding the need for interpretation of low-level user actions for log analysis. We validate the efficiency and effectiveness of the proposed tactic identification method using logs of two reference search systems of different natures: a product search system and a video search system. With the identified tactics, we perform a series of novel log analyses in terms of entropy rate of user search tactic sequences, demonstrating how this type of analysis allows comparisons of user search behaviours across systems of different nature and design. This analysis provides insights not achievable with traditional log analysis.     

Tracking and recognizing emotions in short text messages from online chatting services

To automate the process of emotion recognition, in this study, we develop a computational approach for continuously tracking and analyzing users’ emotions while chatting online. Our work has several unique features: it provides relative probabilities of possible emotions for a word, constructs a distribution for each chatting message accordingly, performs a clustering procedure for the message distribution, and aggregates the emotions of continuous chatting sentences to draw the conclusion. To evaluate the proposed approach, we conducted experiments in two phases. The first phase was to evaluate the effectiveness of the proposed computational approach in analyzing the chatting sentences. The participants were asked to focus on tagging emotions toward each sentence for a pre-designed dialogue. The second phase involves a real-time chatting between two online users. The participants were asked to choose topics and freely chat with each other. The messages were analyzed, and the results were provided to the users for their evaluations. The results show that our approach is both effective and efficient in tracking the emotions of chatting users. Additional analyses and further discussions were carried out to further evaluate the quantitative experimental results. All the findings confirmed the usefulness and feasibility of the presented approach.     

IT artifact bias: How exogenous predilections influence organizational information system paradigms

Efforts in IS research have long sought to bridge the gap between the information technology (IT) function and strategic business interests. People perceive affordances (possibilities for action) in information technology artifacts differently as cognitive structures (schema) which bias individual focus. This study explores how an individual's tendency to perceive the ‘trees’ in an IT ‘forest’ (artifact preference) affects their assessment of efforts to achieve more effective IT outcomes. The effect is demonstrated using a relatively simple IT success model. Further, in a sample of 120 survey responses supported by ten semi-structured interviews, we demonstrate that job role and organizational IT complexity systematically impact artifact perception. A better understanding of IT artifact bias promises to help organizations better assess information systems.     

Recognizing fake information through a developed feature scheme: A user study of health misinformation on social media in China

This study aims at helping people recognize health misinformation on social media in China. A scheme was first developed to identify the features of health misinformation on social media based on content analysis of 482 pieces of health information from WeChat, a social media platform widely used in China. This scheme was able to identify salient features of health misinformation, including exaggeration/absolutes, induced text, claims of being unique and secret, intemperate tone or language, and statements of excessive significance and likewise. The scheme was then evaluated in a user-centred experiment to test if it is useful in identifying features of health misinformation. Forty-four participants for the experimental group and 38 participants for the control group participated and finished the experiment, which compared the effectiveness of these participants in using the scheme to identify health misinformation. The results indicate that the scheme is effective in terms of improving users’ capability in health misinformation identification. The results also indicate that the participants’ capability of recognizing misinformation in the experimental group has been significantly improved compared to those of the control group. The study provides insights into health misinformation and has implications in enhancing people's online health information literacy. It informs the development of a system that can automatically limit the spread of health misinformation. Moreover, it potentially improves users’ online health information literacy, in particular, under the circumstances of the COVID-19 pandemic.