Consumers rely on sources of information to learn about products and make informed purchasing decisions. In fact, one of the first factors consumer consider when evaluating product information, is the source of that information. Yet despite the importance of the source, research on this topic is sporadic, leaving my unanswered questions. This dissertation advances our understanding of how three different sources of information influence consumers' perceptions and decision making. In the first study, we examine two sources (consumer originated and third party) to determine which one dominates in a persuasion episode. We find consumers overwhelmingly prefer consumer originated versus third party sources because they believe fellow consumers convey information that is diagnostic of future product experiences. In our second study, we show how a subtle firm-dominated characteristic, firm size, influences manufacturing assumptions and purchase behavior. We find consumers prefer small to large firms for unique products, because they assume small firms have a high degree of human intervention in the manufacturing process. / Doctor of Philosophy / Consumers rely on sources of information to learn about products and make informed purchasing decisions. In fact, one of the first factors consumer consider when evaluating product information, is the source of that information. Yet despite the importance of the source, research on this topic is sporadic, leaving my unanswered questions. This dissertation advances our understanding of how three different sources of information influence consumers' perceptions and decision making. In the first study, we examine two sources (consumer originated and third party) to determine which one dominates in a persuasion episode. We find consumers overwhelmingly prefer consumer originated versus third party sources because they believe fellow consumers convey information that is diagnostic of future product experiences. In our second study, we show how a subtle firm-dominated characteristic, firm size, influences manufacturing assumptions and purchase behavior. We find consumers prefer small to large firms for unique products, because they assume small firms have a high degree of human intervention in the manufacturing process.

Yes / Online shopping is increasingly becoming people's first choice when shopping, as it is very convenient to choose products based on their reviews. Even for moderately popular products, there are thousands of reviews constantly being posted on e-commerce sites. Such a large volume of data constantly being generated can be considered as a big data challenge for both online businesses and consumers. That makes it difficult for buyers to go through all the reviews to make purchase decisions. In this research, we have developed models based on machine learning that can predict the helpfulness of the consumer reviews using several textual features such as polarity, subjectivity, entropy, and reading ease. The model will automatically assign helpfulness values to an initial review as soon as it is posted on the website so that the review gets a fair chance of being viewed by other buyers. The results of this study will help buyers to write better reviews and thereby assist other buyers in making their purchase decisions, as well as help businesses to improve their websites.

Context. There has been a remarkable growth of the mobile game industry since the raging pandemic covid-19 destroyed many businesses across several industries [1]. Nowadays mobile gaming has been one of the highest performing industries globally, raking in more billions in revenue [1,2]. Understanding the direction and aspects to improve the quality of products and reduce the cost is important for a mobile gaming company to stand out. There is a plethora of literature on how to improve the related product quality [3]. One of them is to analyze and optimize the various requirements in each version update, and how these requirements could be elicited from the company’s development plan and user feedback. Specifically, mobile game companies would review the user comments of their products from various application platforms such as Google Play and Apple store, select the informative comments with specific user requirements according to their own standard, and finally elicit and then implement these requirements in the follow-up version updates. During this process, it is important to control the lead time---the time cost for mobile game companies to review and select the valuable user comments, make decisions to apply the changes, make a development plan afterwards and finally put it into action. In the current increasingly intense competitive environment, time-based dimensions of a product such as the lead-time are becoming an increasingly important component in assessing strategic advantage, since having products early increases the possible market introduction window. Meanwhile, traditional long lead times and high inventory levels may be less appropriate and more costly endeavors that may not even achieve product parity [4]. To compress the product lead time was the priority task to help companies keep their competitiveness [5]. To fulfil this aim, fundamental changes must be made in every function that affects the delivery of the product. However, most existing literature focuses on the lead time in the traditional software industry, which can be different in the case of the mobile game apps. We herein in this paper explore the contents of lead time in the mobile gaming industry. We designed a series of steps to explore the real situation of lead time in the mobile gaming industry. Differences between mobile gaming and traditional software industries are also of interest to be explored.       Objectives. The main purpose of our research was to study the lead time which would be caused during the process of implementing users’ requirements. We tried to achieve the purpose from two aspects: First, we investigated whether there were differences in the lead time of different requirement types. Second, we investigated whether the lead time differences existed in different types of mobile games.   Methods. Our group used Case Study as the main research method to investigate the lead time in real cases.   Results. .First, there were differences in the lead time of implementing different types of requirements. Such as the lead time of bug fix types of requirements would be shorter than feature added types of requirements. Second, different types of mobile game apps had differences in the lead time. For example, MOBA games would take longer time on Function update or Feature request types of requirements, and FPS games would take longer time on exclusive event types of requirements. The details would be shown in part 4.2 and 4.3.   Conclusions. Two research questions in our thesis were answered. When mobile game companies dealt with requirements in user feedback, the lead time objectively existed. We could calculate the length of the lead time of different types of requirements. Moreover, different types of requirements had various lead times. For example, the lead time caused by bug fixing requirement would be shorter compared with that of adding new functions. And this research provided some fundamental results to both academic field and mobile game industry field.   Keywords: Mobile game apps, User reviews, User requirements, Lead time

This research comprises three interconnected studies, all anchored in the usability evaluation of mobile education applications, with guidance from the well-established Jakob Nielsen factors to heuristic evaluation. The first study delves into the analysis of mobile application reviews using a deep learning model and machine learning to unearth usability issues. In the second study, we examine the usability of two prominent educational applications, Canvas and Blackboard, integrated within Prince Sattam bin Abdulaziz University (PSAU) and at the University of North Texas (UNT) from a student-oriented perspective. Through the synthesis of findings and insights from antecedent studies, we seek to augment the current body of knowledge and offer realistic recommendations for the enhancement of mobile education application usability. Our findings have the potential to improve the efficacy of platforms, offering developers a roadmap to refine application features and optimize the learning experience for both educators and learners.

Today many companies exist and market their products and services on social medias, and therefore may receive reviews and thoughts from their end-users directly in these social medias. Reading every text by hand can be time-consuming, so by analysing the sentiment for all texts give the companies an overview how positive or negative the users are on a specific subject. Sentiment analysis is a feature that Beanloop AB is interested in implementing in their future projects and this thesis research problem was to investigate how deep learning could be used for this task. It was done by conducting an experiment with deep learning and neural networks. Several convolutional neural network models were implemented with different settings to find a combination of settings that gave the highest accuracy on the given test dataset. There were two different kind of models, one kind classifying positive and negative, and the second classified the previous two categories but also neutral. The training dataset and the test dataset contained data from two recommendation sites, www.reco.se and se.trustpilot.com. The final result shows that when classifying three categories (positive, negative and neutral) the models had problems to reach an accuracy at 85%, were only one model reached 80% accuracy as best on the test dataset. However, when only classifying two categories (positive and negative) the models showed very good results and reached almost 95% accuracy for every model.

The goal of this thesis is to support the automated identification of accessibility in user reviews or bug reports, to help technology professionals prioritize their handling, and, thus, to create more inclusive apps. Particularly, we propose a model that takes as input accessibility user reviews or bug reports and learns their keyword-based features to make a classification decision, for a given review, on whether it is about accessibility or not. Our empirically driven study follows a mixture of qualitative and quantitative methods. We introduced models that can accurately identify accessibility reviews and bug reports and automate detecting them. Our models can automatically classify app reviews and bug reports as accessibility-related or not so developers can easily detect accessibility issues with their products and improve them to more accessible and inclusive apps utilizing the users' input. Our goal is to create a sustainable change by including a model in the developer's software maintenance pipeline and raising awareness of existing errors that hinder the accessibility of mobile apps, which is a pressing need. In light of our findings from the Blackboard case study, Blackboard and the course material are not easily accessible to deaf students and hard of hearing. Thus, deaf students find that learning is extremely stressful during the pandemic.

This thesis deals with knowledge discovery from social media. This thesis is focused on feature based opinion mining from user reviews. In theoretical part were described methods of opinion mining and natural language processing. Main parts of this thesis were design and implementation of library for opinion mining based on Stanford Parser and lexicon WordNet. For feature identi cation was used dependency grammar, implicit features were mined with method CoAR and opinions were classi ed with supervised algorithm. Finally were given experiments with implemented library and examples of usage.

Denna studie undersöker användarrecensioners påverkan på konsumenters beslutsprocess vid köp av produkter eller tjänster och faktorer som påverkar förtroendet för dessa recensioner. Studien visar att användarrecensioner har en betydande inverkan på konsumenters köpbeslut, med subjektiva normer och upplevd beteendekontroll som viktiga faktorer i beslutsprocessen. Det finns signifikanta skillnader i preferenser och beteende mellan olika åldersgrupper. Studien bidrar till ökad förståelse för konsumenters beteende och preferenser vid online-shopping och ger vägledning för framtida forskning inom detta område. Företag och e-handelsplattformar kan använda studiens insikter för att förbättra sina produkter, tjänster och marknadsföringsstrategier, genom att ta hänsyn till användarrecensioners betydelse och de faktorer som påverkar konsumenters förtroende för dessa recensioner. / This study examines the impact of user reviews on consumers decision-making process when purchasing products or services and factors that influence trust in these reviews. The study shows that user reviews have a significant influence on consumers purchasing decisions, with subjective norms and perceived behavioral control as important factors in the decision-making process. There are significant differences in preferences and behavior among different age groups. The study contributes to a better understanding of consumer behavior and preferences in online shopping and provides guidance for future research in this area. Companies and e-commerce platforms can use the insights from the study to improve their products, services, and marketing strategies by considering the importance of user reviews and the factors that influence consumers trust in these reviews.

Manuell granskning av användarrecensioner för att extrahera relevant informationkan vara en tidskrävande process. Denna rapport har undersökt om stora språkmodeller kan användas för att sammanfatta, extrahera och analysera nyckelinformation från recensioner, samt hur en sådan applikation kan konstrueras.  Det visade sig att olika modeller presterade olika bra beroende på mätvärden ochviktning mellan recall och precision. Vidare visade det sig att fine-tuning av språkmodeller som Llama 3 förbättrade prestationen vid klassifikation av användbara recensioner och ledde, enligt vissa mätvärden, till högre prestation än större språkmodeller som Chat-Bison. För engelskt översatta recensioner hade Llama 3:8b:Instruct, Chat-Bison samt den fine-tunade versionen av Llama 3:8b ett F4-makro-score på 0.89, 0.90 och 0.91 respektive. Ytterligare ett resultat är att de större modellerna Chat-Bison, Text-Bison och Gemini, presterade bättre i fallet för generering av sammanfattande texter, än de mindre modeller som testades vid inmatning av flertalet recensioner åt gången.  Generellt sett presterade språkmodellerna också bättre om recensioner först översattes till engelska innan bearbetning, snarare än då recensionerna var skrivna i originalspråk där de majoriteten av recensionerna var skrivna på svenska. En annan lärdom från förbearbetning av recensioner är att antal anrop till dessa språkmodeller kan minimeras genom att filtrera utifrån ordlängd och betyg.  Utöver språkmodeller visade resultaten att användningen av vektordatabaser och embeddings kan ge en större överblick över användbara recensioner genom vektordatabasers inbyggda förmåga att hitta semantiska likheter och samla liknande recensioner i kluster. / Manually reviewing user reviews to extract relevant information can be a time consuming process. This report investigates if large language models can be used to summarize, extract, and analyze key information from reviews, and how such anapplication can be constructed.  It was discovered that different models exhibit varying degrees of performance depending on the metrics and the weighting between recall and precision. Furthermore, fine-tuning of language models such as Llama 3 was found to improve performance in classifying useful reviews and, according to some metrics, led to higher performance than larger language models like Chat-bison. Specifically, for English translated reviews, Llama 3:8b:Instruct, Chat-bison, and Llama 3:8b fine-tuned had an F4 macro score 0.89, 0.90, 0.91 respectively. A further finding is that the larger models, Chat-Bison, Text-Bison, and Gemini performed better than the smaller models that was tested, when inputting multiple reviews at a time in the case of summary text generation.  In general, language models performed better if reviews were first translated into English before processing rather than when reviews were written in the original language where most reviews were written in Swedish. Additionally, another insight from the pre-processing phase, is that the number of API-calls to these language models can be minimized by filtering based on word length and rating. In addition to findings related to language models, the results also demonstrated that the use of vector databases and embeddings can provide a greater overview of reviews by leveraging the databases’ built-in ability to identify semantic similarities and cluster similar reviews together.