DISSERTATION Submitted in partial (50%) fulfilment of the requirements for the degree MAGISTER TECHNOLOGIAE in BUSINESS INFORMATION SYSTEMS in the FACULTY OF BUSINESS INFORMATICS at the CAPE PENINSULA UNIVERSITY OF TECHNOLOGY 2005 / The growth of the World Wide Web has spawned a wide collection of new information sources, which has also left users with the daunting task of determining which sources are valid. Most users rely on the web because of the low cost of information retrieval. Other advantages of the web include the convenience in terms of time and access as well as the ability to easily record results. It is also claimed that the web has evolved into a powerful business tool. Examples include highly popular business services such as Amazon.com and Kalahari.net. It is estimated that around 80% of users utilise search engines to locate information on the Internet. This of course places emphasis on the underlying importance of webpages being listed on search engines indices. It is in the interest of any company to pursue a strategy for ensuring a high search engine ranking for their e-Commerce website. This will result in more visits from users and possibly more sales. One of the strategies for ensuring a high search engine ranking is the placement of keywords in the body text section of a webpage. Empirical evidence that the placement of keywords in certain areas of the body text will have an influence on the websites’ visibility to search engines could not be found. The author set out to prove or disprove that keywords in the body text of a webpage will have a measurable effect on the visibility of a website to search engine crawlers. From the findings of this research it will be possible to create a guide for e- Commerce website authors on the usage, placing and density of keywords within their websites. This guide, although it will only focus on one aspect of search engine visibility, could help e-Commerce websites to attract more visitors and to become more profitable.

Thesis (DTech (Informatics))--Cape Peninsula University of Technology, 2017. / Any e-commerce venture using a website as main shop-front should invest in marketing their website. Previous empirical evidence shows that most Search Engine Marketing (SEM) spending (approximately 82%) is allocated to Pay Per Click (PPC) campaigns while only 12% was spent on Search Engine Optimisation (SEO). The remaining 6% of the total spending was allocated to other SEM strategies. No empirical work was found on how marketing expenses compare when used solely for either the one or the other of the two main types of SEM. In this study, a model will be designed to guide the development of a dual SEM strategy.

Graph-structured databases are widely prevalent, and the problem of effective search and retrieval from such graphs has been receiving much attention recently. For example, the Web can be naturally viewed as a graph. Likewise, a relational database can be viewed as a graph where tuples are modeled as vertices connected via foreign-key relationships. Keyword search querying has emerged as one of the most effective paradigms for information discovery, especially over HTML documents in the World Wide Web. One of the key advantages of keyword search querying is its simplicity – users do not have to learn a complex query language, and can issue queries without any prior knowledge about the structure of the underlying data. The purpose of this dissertation was to develop techniques for user-friendly, high quality and efficient searching of graph structured databases. Several ranked search methods on data graphs have been studied in the recent years. Given a top-k keyword search query on a graph and some ranking criteria, a keyword proximity search finds the top-k answers where each answer is a substructure of the graph containing all query keywords, which illustrates the relationship between the keyword present in the graph. We applied keyword proximity search on the web and the page graph of web documents to find top-k answers that satisfy user’s information need and increase user satisfaction. Another effective ranking mechanism applied on data graphs is the authority flow based ranking mechanism. Given a top-k keyword search query on a graph, an authority-flow based search finds the top-k answers where each answer is a node in the graph ranked according to its relevance and importance to the query. We developed techniques that improved the authority flow based search on data graphs by creating a framework to explain and reformulate them taking in to consideration user preferences and feedback. We also applied the proposed graph search techniques for Information Discovery over biological databases. Our algorithms were experimentally evaluated for performance and quality. The quality of our method was compared to current approaches by using user surveys.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第22805号 / 情博第735号 / 新制||情||126(附属図書館) / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 吉川 正俊, 教授 森 信介, 教授 田島 敬史 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

The 2018 Swedish general election saw the largest collective polling error so far in the twenty-first century. As in most other advanced democracies Swedish pollsters have faced extensive challenges in the form of declining response rates. To deal with this problem a new method based on search query data is proposed. This thesis predicts the Swedish general election using Google Trends data by introducing three models based on the assumption, that during the pre-election period actual voters of one party are searching for that party on Google. The results indicate that a model that exploits information about searches close to the election is in general a good predictor. However, I argue that this has more to do with the underlying weight this model is based on and little to do with Google Trends data. However, more analysis needs to be done before any direct conclusion, about the use of search query data in election prediction, can be drawn.

<div>When a user types in a search query in an Information Retrieval system, a list of top ‘n’ ranked documents relevant to the query are returned by the system. Relevant means not just returning documents that belong to the same category as that of the search query, but also returning documents that provide a concise answer to the search query. Determining the relevance of the documents is a significant challenge as the classic indexing techniques that use term/word frequencies do not consider the term (word) dependencies or the impact of previous terms on the current words or the meaning of the words in the document. There is a need to model the dependencies of the terms in the text data and learn the underlying statistical patterns to find the similarity between the user query and the documents to determine the relevancy.</div><div><br></div><div>This research proposes a solution based on Markov Random Fields (MRF) and Restricted Boltzmann Machines (RBM) to solve the problem of term dependencies and learn the underlying patterns to return documents that are very similar to the user query.</div>

Internet search has changed significantly since its beginning and it has also changed the way of information retrieval. Firstly, network search tools were created. However, greater development of internet search tools came after the creation of the Web. One of the first internet search tools were the web directories, such as Yahoo! or content directory Open Directory Project. Nowadays, web search engines are the most commonly used. Apart from general web search engines, there are also specialized or web search engines for particular aim or function, such as DuckDuckGo aimed at privacy, Yandex or Seznam.cz aimed at specific region or computational search engine WolframAlpha. Multimedia search and search adapted for mobile devices is technology trend in the field of internet search. Personalization, localization and social search belong among the contemporary trends. Semantic search is another long-lasting trend.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第19119号 / 情博第565号 / 新制||情||99(附属図書館) / 32070 / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 田中 克己, 教授 吉川 正俊, 教授 黒橋 禎夫 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第20030号 / 情博第625号 / 新制||情||109(附属図書館) / 33126 / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 田中 克己, 教授 吉川 正俊, 教授 黒橋 禎夫 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

User click modeling in web search is most commonly done through probabilistic graphical models. Due to the successful use of machine learning techniques in other fields of research, it is interesting to evaluate how machine learning can be applied to click modeling. In this thesis, modeling is done using recurrent neural networks trained on a distributed representation of the state of the art user browsing model (UBM). It is further evaluated how extending this representation with a set of latent variables that are easily derivable from click logs, can affect the model's prediction performance. Results show that a model using the original representation does not perform very well. However, the inclusion of simple variables can drastically increase the performance regarding the click prediction task. For which it manages to outperform the two chosen baseline models, which themselves are well performing already. It also leads to increased performance for the relevance prediction task, although the results are not as significant. It can be argued that the relevance prediction task is not a fair comparison to the baseline functions, due to them needing more significant amounts of data to learn the respective probabilities. However, it is favorable that the neural models manage to perform quite well using smaller amounts of data. It would be interesting to see how well such models would perform when trained on far greater data quantities than what was used in this project. Also tailoring the model for the use of LSTM, which supposedly could increase performance even more. Evaluating other representations than the one used would also be of interest, as this representation did not perform remarkably on its own. / Klickmodellering av användare i söksystem görs vanligtvis med hjälp av probabilistiska modeller. På grund av maskininlärningens framgångar inom andra områden är det intressant att undersöka hur dessa tekniker kan appliceras för klickmodellering. Detta examensarbete undersöker klickmodellering med hjälp av recurrent neural networks tränade på en distribuerad representation av en populär och välpresterande klickmodell benämnd user browsing model (UBM). Det undersöks vidare hur utökandet av denna representation med statistiska variabler som enkelt kan utvinnas från klickloggar, kan påverka denna modells prestanda. Resultaten visar att grundrepresentationen inte presterar särskilt bra. Däremot har användningen av simpla variabler visats medföra drastiska prestandaökningar när det kommer till att förutspå en användares klick. I detta syfte lyckas modellerna prestera bättre än de två baselinemodeller som valts, vilka redan är välpresterande för syftet. De har även lyckats förbättra modellernas förmåga att förutspå relevans, fastän skillnaderna inte är lika drastiska. Relevans utgör inte en lika jämn jämförelse gentemot baselinemodellerna, då dessa kräver mycket större datamängder för att nå verklig prestanda. Det är däremot fördelaktigt att de neurala modellerna når relativt god prestanda för datamängden som använts. Det vore intressant att undersöka hur dessa modeller skulle prestera när de tränas på mycket större datamängder än vad som använts i detta projekt. Även att skräddarsy modellerna för LSTM, vilket borde kunna öka prestandan ytterligare. Att evaluera andra representationer än den som användes i detta projekt är också av intresse, då den använda representationen inte presterade märkvärdigt i sin grundform.