Contextual text mining

With the dramatic growth of text information, there is an increasing need for powerful text mining systems that can automatically discover useful knowledge from text. Text is generally associated with all kinds of contextual information. Those contexts can be explicit, such as the time and the location where a blog article is written, and the author(s) of a biomedical publication, or implicit, such as the positive or negative sentiment that an author had when she wrote a product review; there may also be complex context such as the social network of the authors. Many applications require analysis of topic patterns over different contexts. For instance, analysis of search logs in the context of the user can reveal how we can improve the quality of a search engine by optimizing the search results according to particular users; analysis of customer reviews in the context of positive and negative sentiments can help the user summarize public opinions about a product; analysis of blogs or scientific publications in the context of a social network can facilitate discovery of more meaningful topical communities. Since context information significantly affects the choices of topics and language made by authors, in general, it is very important to incorporate it into analyzing and mining text data. In general, modeling the context in text, discovering contextual patterns of language units and topics from text, a general task which we refer to as Contextual Text Mining, has widespread applications in text mining. In this thesis, we provide a novel and systematic study of contextual text mining, which is a new paradigm of text mining treating context information as the ``first-class citizen.'' We formally define the problem of contextual text mining and its basic tasks, and propose a general framework for contextual text mining based on generative modeling of text. This conceptual framework provides general guidance on text mining problems with context information and can be instantiated into many real tasks, including the general problem of contextual topic analysis. We formally present a functional framework for contextual topic analysis, with a general contextual topic model and its various versions, which can effectively solve the text mining problems in a lot of real world applications. We further introduce general components of contextual topic analysis, by adding priors to contextual topic models to incorporate prior knowledge, regularizing contextual topic models with dependency structure of context, and postprocessing contextual patterns to extract refined patterns. The refinements on the general contextual topic model naturally lead to a variety of probabilistic models which incorporate different types of context and various assumptions and constraints. These special versions of the contextual topic model are proved effective in a variety of real applications involving topics and explicit contexts, implicit contexts, and complex contexts. We then introduce a postprocessing procedure for contextual patterns, by generating meaningful labels for multinomial context models. This method provides a general way to interpret text mining results for real users. By applying contextual text mining in the ``context'' of other text information management tasks, including ad hoc text retrieval and web search, we further prove the effectiveness of contextual text mining techniques in a quantitative way with large scale datasets. The framework of contextual text mining not only unifies many explorations of text analysis with context information, but also opens up many new possibilities for future research directions in text mining.

Effects of various salt purity levels on lipid oxidation and sensory characteristics of ground turkey and pork

Salt use in meat products is changing. Consumers desire sea salt which may also contain trace metals and the government is demanding a reduction in sodium. Therefore a need exists to understand how varying impurity levels in salt affect meat quality. This study evaluated the effects of various salt preparations on lipid oxidation, sensory characteristics, protein extractability, and bind strength of ground turkey and pork. This study was a completely randomized design with 5 treatment groups and 6 replications in 2 species. Ground, turkey and pork meat was formulated into one hundred and fifty gram patties with sodium chloride (1%) containing varying amounts of metal impurities (copper, iron, and manganese). Samples were randomly assigned to frozen storage periods of 0, 3, 6, and 9 weeks. After storage, samples were packaged in PVC overwrap and stored under retail display for 5 days. Samples were evaluated for proximate analysis to ensure the fat content was similar for all of the starting material.Thiobarbituric acid reactive substances (TBARS) were determined on raw and cooked samples to evaluate lipid oxidation. A trained six member sensory panel evaluated the samples at each storage period for saltiness, off flavor, and oxidized odor. Break strength was conducted using a Texture Analyzer and compared with salt soluble proteins (increasing salt concentrations) to evaluate protein extractability characteristics. Statistical analyses were conducted using the MIXED procedure of SAS within repeated measures over time where appropriate. No significant differences were observed among the salt treatments for raw and cooked TBARS when the control group was removed (P>0.05). Sensory panelists detected increased levels of off flavor and oxidized odor over the entire storage duration. Less force was required to break the patties from the control group when compared with the salt treatments (P<0.05). As salt concentration increased salt-soluble protein extraction increased, but there was no effect of salt type. Overall, no meaningful statistical differences among the various salt treatments were observed for all of the parameters evaluated for turkey and pork. Salt at a 1% inclusion rate containing varying levels of copper, iron, and manganese impurities in ground turkey thigh meat and ground pork served as a prooxidant. However, if a meat processor uses a 1% inclusion rate of salt in turkey and pork regardless of impurities included, it is unlikely that differences in shelf life or protein functionality would be observed.