No description available.

Email, chat, instant messaging, blogs, and newsgroups are now common ways for people to interact. Along with these new ways for sending, receiving, and storing messages comes the challenge of organizing, filtering, and understanding them, for which text mining has been shown to be useful. Additionally, it has done so using both content-dependent and content-independent methods.Unfortunately, computer-mediated communication has also provided criminals, terrorists, spies, and other threats to security a means of efficient communication. However, the often textual encoding of these communications may also provide for the possibility of detecting and tracking those who are deceptive. Two methods for organizing, filtering, understanding, and detecting deception in text-based computer-mediated communication are presented.First, message feature mining uses message features or cues in CMC messages combined with machine learning techniques to classify messages according to the sender's intent. The method utilizes common classification methods coupled with linguistic analysis of messages for extraction of a number of content-independent input features. A study using message feature mining to classify deceptive and non-deceptive email messages attained classification accuracy between 60\% and 80\%.Second, speech act profiling is a method for evaluating and visualizing synchronous CMC by creating profiles of conversations and their participants using speech act theory and probabilistic classification methods. Transcripts from a large corpus of speech act annotated conversations are used to train language models and a modified hidden Markov model (HMM) to obtain probable speech acts for sentences, which are aggregated for each conversation participant creating a set of speech act profiles. Three studies for validating the profiles are detailed as well as two studies showing speech act profiling's ability to uncover uncertainty related to deception.The methods introduced here are two content-independent methods that represent a possible new direction in text analysis. Both have possible applications outside the context of deception. In addition to aiding deception detection, these methods may also be applicable in information retrieval, technical support training, GSS facilitation support, transportation security, and information assurance.

No description available.

The theme of Master project is a posibility to use arificial neural networks for textual analysis and automatic categorization of textual documents in editorial programs. The task of the work was to analyze diferent methods of text clasification using diferent neural networks (SOM, Feed Forward, Learning Vector Quantization, etc.). There are much researchers who works on text clasification and artificial neural networks, but there is no practical fitting of such research. In this work I tried to find posibilities and dificulties of practical use of text clasification. I find that very important thing is initial amount and quality of information and not all neural networks fits for solving text categorization problems.

Tyrimo objektas – lietuvių kalbos leksikos italų kilmės žodžiai. Darbo tikslas – pateikti išsamų lietuvių kalbos italų kilmės skolinių aprašą. Medžiaga. Daugiausia naudojantis rašytiniais šaltiniais (visų pirma žodynais), sudaryta skolinių iš italų kalbos duomenų bazė (Lietuvių kalbos italizmų sąvadas – LKIS), į kurią įtraukti 936 semantiniai vienetai. Ginamieji teiginiai ir tyrimo rezultatai. Tradicinis lietuvių kalbotyros požiūris, esą lietuvių kalbos skoliniai skirstytini vien į slavizmus ir germanizmus (be dar keleto iš gretimų kalbų), faktiškai menkina italų ir lietuvių tautų santykių istoriją, perša izoliuotos lietuvių valstybės bei siauro jos gyventojų kultūrinio, socialinio bei politinio akiračio vaizdą. Faktas, kad į lietuvių kalbą skoliniai iš italų kalbos pateko dažniausiai per kalbas tarpininkes (tai įrodo adaptacijos procesų lemiami fonetiniai pakitimai) negali būti pagrindas paneigti jų italų kilmę. Nors iš visų LKIS italizmų tik nedidelė dalis įeina į pagrindinį lietuvių kalbos leksikos fondą (vos apie 7 proc. visų italizmų VDU tekstyne pavartota daugiau nei 1000 kartų), bet apribojus statistiškai apdorojamų italizmų sąrašą, t.y. išmetus italizmus, nesiekiančius tam tikro skaičiaus pavartojimo atvejų, išryškėja tikslesnis italizmų pasiskirstymo pagal semantines grupes vaizdas: 1) 45 proc. visų italizmų sudaro buitinės kalbos žodžiai (tokie kaip autostrada, loterija, moto, pedalas, rizika, sijonas); 2) muzikos terminai siekia beveik penktadalį visų italizmų (... [toliau žr. visą tekstą] / The PhD thesis deals with Italian loanwoards in Lithuanian.

Mental imagery as a form of human cognition is still not well understood, particularly in the area of spatiality. This thesis attempts to find the relationship between the mental images of places created while reading a story (ekphrastic) and the mental images created while viewing a cinematic adaptation of that story. Using Bakhtin’s idea of chronotope, and Panofsky’s theory of iconography, associations can be made between places in text and film that inform the themes that readers/spectators identify and evaluate. Netlytic, an online text analysis tool, permits the analysis of online message board fan opinions of J.R.R. Tolkien’s and Peter Jackson’s The Lord of the Rings according to themes of visualization and of place. Analysis of findings suggests that mental images created from the text and from the filmic adaptation are both passively and actively integrated in order to increase comprehension of spatial elements in Tolkien’s epic.

We present a novel marketing method for consumer trend detection from online user generated content, which is motivated by the gap identified in the market research literature. The existing approaches for trend analysis generally base on rating of trends by industry experts through survey questionnaires, interviews, or similar. These methods proved to be inherently costly and often suffer from bias. Our approach is based on the use of information extraction techniques for identification of trends in large aggregations of social media data. It is cost-effective method that reduces the possibility of errors associated with the design of the sample and the research instrument. The effectiveness of the approach is demonstrated in the experiment performed on restaurant review data. The accuracy of the results is at the level of current approaches for both, information extraction and market research.

Experimentally determining the biological function of a protein is a process known as protein characterization. Establishing the role a specific protein plays is a vital step toward fully understanding the biochemical processes that drive life in all its forms. In order for researchers to efficiently locate and benefit from the results of protein characterization experiments, the relevant information is compiled into public databases. To populate such databases, curators, who are experts in the biomedical domain, must search the literature to obtain the relevant information, as the experiment results are typically published in scientific journals. The database curators identify relevant journal articles, read them, and then extract the required information into the database. In recent years the rate of biomedical research has greatly increased, and database curators are unable to keep pace with the number of articles being published. Consequently, maintaining an up-to-date database of characterized proteins, let alone populating a new database, has become a daunting task. In this thesis, we report our work to reduce the effort required from database curators in order to create and maintain a database of characterized proteins. We describe a system we have designed for automatically identifying relevant articles that discuss the results of protein characterization experiments. Classifiers are trained and tested using a large dataset of abstracts, which we collected from articles referenced in public databases, as well as small datasets of manually labeled abstracts. We evaluate both a standard and a modified naïve Bayes classifier and examine several different feature sets for representing articles. Our findings indicate that the resulting classifier performs well enough to be considered useful by the curators of a characterized protein database. / Thesis (Master, Computing) -- Queen's University, 2010-01-28 18:45:17.249

We introduce a novel Syntax-based Security Testing (SST) framework that uses a protocol specification to effectively perform security testing on text-based communication protocols. A protocol specification of a particular text-based protocol under-tested (TPUT) represents its syntactic grammar and static semantic contracts on the grammar. Mutators written in TXL break the syntactic and semantic constraints of the protocol specification to generate test cases. Different protocol specification testing strategies can be joined together to yield a compositional testing approach. SST is independent of any particular text-based protocols. The power of SST stems from the way it obtains test cases from the protocol specifications. We also use the robust parsing technique with TXL to parse a TPUT. SST has successfully revealed security faults in different text-based protocol applications such as web applications and kOganizer. We also demonstrate SST can mimic the venerable PROTOS Test-Suite: co-http-reply developed by University of Oulu. / Thesis (Ph.D, Computing) -- Queen's University, 2010-04-30 16:01:18.048

No description available.