Context: Mobile application stores like Google Play, Apple store, Windows store have over 3 million apps. Users download the applications from their respective stores and they generally prefer the apps with the highest ratings. In response to the present situation, application stores provided the categories like editor’s choice or top charts, providing better visibility for the applications. Customer reviews play such critical role in the development of the application and the organization, in such case there might be flawed reviews or biased opinions about the application due to many factors. The biased opinions and flawed reviews are likely to cause user review untrustworthiness. The reviews or ratings in the mobile application stores are used by the organizations to make the applications more efficient and more adaptable to the user. The context leads to importance of the user’s review trustworthiness and managing the trustworthiness in the user feedback by knowing the causes of mistrust. Hence, there is a need for a framework to understand the trustworthiness in the user given feedback. Objectives: In the following study the author aims for the accomplishment of the following objectives, firstly, exploring the causes of untrustworthiness in user feedback for an application in the mobile application stores such as google play store. Secondly, Exploring the effects of trustworthiness on the users and developers. Finally, the aim is to propose a framework for managing the trustworthiness in the feedback. Methods: To accomplish the objectives, author used qualitative research method. The data collection method is an interview-based survey that was conducted with 13 participants, to find out the causes of untrustworthiness in the user feedback from user’s perspective and developer’s perspective. Author follows thematic coding for qualitative data analysis. Results:Author identifies 11 codes from the description of the transcripts and explores the relationship among the trustworthiness with the causes. 11 codes were put into 4 themes, and a thematic network is created between the themes. The relations were then analyzed with cost-effect analysis. Conclusions: We conclude that 11 causes effect the trustworthiness according to user’s perspective and 9 causes effect the trustworthiness according to the developer’s perspective, from the analysis. Segregating the trustworthy feedback from the untrustworthy feedback is important for the developers, as the next releases should be planned based on that. Finally, an inclusion and exclusion criteria to help developers manage trustworthy user feedback is defined.

We present INCREMENT, a cluster refinement algorithm which utilizes user feedback to refine clusterings. INCREMENT is capable of improving clusterings produced by arbitrary clustering algorithms. The initial clustering provided is first sub-clustered to improve query efficiency. A small set of select instances from each of these sub-clusters are presented to a user for labelling. Utilizing the user feedback, INCREMENT trains a feature embedder to map the input features to a new feature space. This space is learned such that spatial distance is inversely correlated with semantic similarity, determined from the user feedback. A final clustering is then formed in the embedded space. INCREMENT is tested on 9 datasets initially clustered with 4 distinct clustering algorithms. INCREMENT improved the accuracy of 71% of the initial clusterings with respect to a target clustering. For all the experiments the median percent improvement is 27.3% for V-Measure and is 6.08% for accuracy.

Near-infrared spectroscopy (NIRS) in an imaging technique that has gained much attention in brain-computer interfaces (BCIs). Previous NIRS-BCI studies have primarily employed temporal features, derived from the time course of hemodynamic activity, despite potential value contained in the spatial attributes of a response. In an initial offline study, we investigated the value of using joint spatial-temporal pattern classification with dynamic NIR topograms to differentiate intentional cortical activation from rest. With the inclusion of spatiotemporal features, we demonstrated a significant increase in achievable classification accuracies from those obtained using temporal features alone (p < 10-4). In a second study, we evaluated the feasibility of implementing joint spatial-temporal pattern classification in an online system. We developed an online system-paced NIRS-BCI, and were able to differentiate two cortical states with high accuracy (77.4±10.5%). Collectively, these findings demonstrate the value of including spatiotemporal features in the classification of functional NIRS data for BCI applications.

Due to the popularity of social media and an increase in the engagement of social care, traditional word-of-mouth communications has been replaced by electronic word-of-mouth (e-WOM). Facebook, the most popular website in the United States, is home to nearly 18 million brand or business pages and may be accessed by social media-users aiming to engage in social care, which is customer service via social media. Extending existing research, this study employed in-depth interviews to determine whether or not social media-users are affected by the feedback of other users on restaurants' Facebook pages. The results of this study suggest that Facebook is being used as a tool to attain user feedback regarding restaurants and is perceived as a credible tool. The results also suggest that social media-users are mainly affected by others' user feedback when they are researching a restaurant they have not yet experienced. Finally, the findings of this study suggest that restaurants using Facebook should respond to all types of user feedback, since this practice may result in providing social media-users with a more positive perception of the restaurant.

Near-infrared spectroscopy (NIRS) in an imaging technique that has gained much attention in brain-computer interfaces (BCIs). Previous NIRS-BCI studies have primarily employed temporal features, derived from the time course of hemodynamic activity, despite potential value contained in the spatial attributes of a response. In an initial offline study, we investigated the value of using joint spatial-temporal pattern classification with dynamic NIR topograms to differentiate intentional cortical activation from rest. With the inclusion of spatiotemporal features, we demonstrated a significant increase in achievable classification accuracies from those obtained using temporal features alone (p < 10-4). In a second study, we evaluated the feasibility of implementing joint spatial-temporal pattern classification in an online system. We developed an online system-paced NIRS-BCI, and were able to differentiate two cortical states with high accuracy (77.4±10.5%). Collectively, these findings demonstrate the value of including spatiotemporal features in the classification of functional NIRS data for BCI applications.

Context. Nowadays, mobile applications and services have occupied an essential part in our daily life. We use them to fulfill our needs for communication, news, or entertainment. Within a fierce competitive market, mobile applications need continually improvement through collections of user feedback to satisfy users’ needs. However, in mobile applications, lack of a comprehensive consideration in designing feedback mechanism makes it difficult to efficiently collect user feedback. It shows only approximate one third online user reviews that contain helpful information for improvement. In addition, users may be disturbed by feedback request, result in rejecting to provide feedback. Objectives. This study aims to provide a comprehensive consideration for elicitation of user feedback in mobile applications. Methods. This study followed a mixed qualitative-quantitative research approach. Firstly, we conducted an experiment and a semi-structured interview to investigate how do users provide feedback when they are using a mobile application. Then a content analysis and a statistical analysis were conducted for analyzing collected data.    Results. Users’ preference of feedback approaches and the encouraging/discouraging factors for users to provide feedback were identified. We also assessed user-perceived suitable timings for interruption of feedback request. Conclusions. The result shows, generally, users prefer to provide feedback when asked by feedback request. Three encouraging factors and Three discouraging factors are identified. The beginning of mobile application execution is perceived as best moment for interruption of feedback request. In addition, this study also provides a three-time-dimensions approach for researching disturbances caused by interruption of feedback request as well as other peripheral information.

Context. Software evaluation is a research hotspot of both academia and industry. Users as the ultimate beneficiary of software products, their evaluation becomes more and more importance. In the real word, the users’ evaluation outcomes as the reference for end-users selecting products, and for project managers comparing their product with competitive products. A mobile application is a special software, which is facing the same situation. It is necessary to find and test an evaluation method for a mobile application which based on users’ feedback and give more reference for different stakeholders. Objectives. The aim of this thesis is to apply and evaluate AF in mobile application features rating. There are three kinds of people, and three processes are involved in a rating method applying process, rating designers in rating design process, rating providers in the rating process, and end-users in selecting process. Each process has the corresponding research objectives and research questions to test the applicability of AF method and the satisfaction of using AF and using AF rating outcomes. Methods. The research method of this thesis is a mixed method. The thesis combined experiment, questionnaire, and interview to achieve the research aim. The experiment is using for constructing a rating environment to simulate mobile application evaluation in the real world and test the applicability of AF method. Questionnaire as a supporting method utilizing for collecting the ratings from rating providers. And interviews are used for getting the satisfaction feedback of rating providers and end-users. Results. In this thesis, all AF use conditions are met, and AF evaluation system can be built in mobile application features rating. Comparing with existing method rating outcomes, the rating outcomes of AF are correct and complete. Although, the good feelings of end-users using AF rating outcomes to selecting a product, due to the complex rating process and heavy time cost, the satisfaction of rating providers is negative. Conclusions. AF can be used in mobile application features rating. Although there are many obvious advantages likes more scientific features weight, and more rating outcomes for different stakeholders, there are also shortages to improve such as complex rating process, heavy time cost, and bad information presentation. There is no evidence AF can reply the existing rating method in apps stores. However, there is still research value of AF in future work.

In several applications, when anomalies are detected, human experts have to investigate or verify them one by one. As they investigate, they unwittingly produce a label - true positive (TP) or false positive (FP). In this thesis, we propose two methods (PAD and Clustering-based OMD/OJRank) that exploit this label feedback to minimize the FP rate and detect more relevant anomalies, while minimizing the expert effort required to investigate them. These two methods iteratively suggest the top-1 anomalous instance to a human expert and receive feedback. Before suggesting the next anomaly, the methods re-ranks instances so that the top anomalous instances are similar to the TP instances and dissimilar to the FP instances. This is achieved by learning to score anomalies differently in various regions of the feature space (OMD-Clustering) and by learning to score anomalies based on the distance to the real anomalies (PAD). An experimental evaluation on several real-world datasets is conducted. The results show that OMD-Clustering achieves statistically significant improvement in both detection precision and expert effort compared to state-of-the-art interactive anomaly detection methods. PAD reduces expert effort but there was no improvement in detection precision compared to state-of-the-art methods. We submitted a paper based on the work presented in this thesis, to the ECML/PKDD Workshop on "IoT Stream for Data Driven Predictive Maintenance".

Background: With the increasing number of software users using social media forums, providing feedback about the OSS projects, the developer’s need to address this feedback to understand the requirements of an OSS project. As different tools support different structures for the feedback, the need to classify, prioritize and filter them into a fundamental set of categories persists. Some of the feedback includes images from users, along with the text. These images may vary from a screenshot of the bug, encountered by the user to a code snippet modification as required by the user. The significance of how these images help the developers in fixing the bug is not clear. Objectives: This thesis aims to identify the underlying advantages of using images in the feedback or bug report submitted by the user for an OSS project to the developers. The goal is to find the extent to which different image attributes help the developer’s in understanding the issue suggested in the feedback or bug report. The research also aims to classify the view of practitioners regarding which image attributes affect the most and to propose a simple DSS model that can possibly be used by users and developers while attaching images in the feedback or bug reports. Methods: In this research, we have conducted an empirical study using systematic mapping and a survey study. We identified 28 research articles form systematic mapping using a search string and snowballing process to extract different image attributes. To triangulate and verify the results of the systematic map, we have conducted an online questionnaire replied by 32 respondents experienced in contributing to the OSS community. The usability of the image attributes has been evaluated from the responses received. Both quantitative and descriptive statistical analysis techniques were used to analyze the results. Results: From the 28 research articles identified for the systematic mapping study, we have extracted 11 image attributes that influence the developers in interpreting the software requirements from the images attached to feedback or bug reports. Of the identified image attributes, image quality and image resolution are considered to be the most useful attributes by the survey respondents. Moreover, two new image attributes (timestamp and steps to reproduce) are reported from the survey study. Conclusions: The identification and validation of the image attributes suggest the potential use of images in feedback and bug reports. Furthermore, these image attributes provide additional information to the developers in understanding the software requirements from the users perspective clearly. We propose a simple DSS model that can be used by the users and the developers before attaching an image along with the feedback or the bug reports to the developing OSS communities to promote further usage of images in feedback and bug reports for OSS.

Customer feedback is essential for improving a company's products or services and increasing customer satisfaction. Despite its value, user involvement faces many challenges, such as low user motivation and feedback with missing context information. To increase the chance of collecting user feedback, the process must be fast, easy, and well-integrated into the system or product.  In this thesis, a suitable way of designing a high-fidelity (Hi-Fi) prototype of a reactive feedback feature that improves the ease of submitting end-user feedback and enriching it with sufficient information to streamline the interpretation and handling process has been investigated. This was done by following the Design Thinking method and its five phases. In the first phase of the process, Empathize, information about the end-users' and the product teams' pain points, wants, and needs regarding the current feedback process were gathered through interviews. A literature study and research of existing feedback tools were also conducted to build a broader knowledge about the subject. The collected data was organized and analyzed during the second phase, Define, through affinity diagramming, a customer journey map, and defining user need statements. In the third phase, Ideate, a wide range of design solutions to the identified problems and user need statements were generated during a Crazy 8 workshop and initial sketching. The two final phases, Prototype and Test, consisted of three iterations of creating and evaluating prototypes through an expert review, a usability test, a heuristic evaluation, and a final usability test.  The two major identified pain points were the product team expressed that customer feedback is often difficult to interpret due to missing context information, and that end users have to go through a long and laborious procedure to provide feedback. End-users wanted an easy and fast way to submit a wide range of feedback to have some impact on the product's future improvement, and the product team wanted to collect as much sufficient information as possible to facilitate the interpretation and handling process. The study explores the challenges of including predefined feedback options and a prioritization feature to enhance the interpretation and management of feedback while maintaining ease of use. The prototype includes the possibility to attach annotated screenshots and screen recordings and automatically collects contextual data to address the lack of information and simplify and speed up the feedback process for end-users. The final usability test resulted in positive feedback and showed that the suggested feedback feature enables end-users to provide feedback quickly and easily while providing the product team with the most necessary information. The result also gives a first indication that the feedback feature will increase the end-user involvement in the product's future development.