Motorola Corporation

Intuit, Inc.

Giovanni Seni

John Lome Seybold

Meng Chen

Jens Nagel

Pierre Demartines

The disclosed embodiments provide a system for facilitating sentiment analysis. During operation, the system obtains a set of training data that includes a first set of content items containing words associated with a domain, a set of sentiment scores for the first set of content items, and a set of outcomes associated with the first set of content items. Next, the system uses the training data to train a statistical model for performing sentiment analysis that is specific to the domain. The system then enables use of the statistical model in generating a set of domain-specific sentiment scores for a second set of content items containing words associated with the domain.

Domain-specific sentiment keyword extraction with weighted labels

A method and system for written input and subsequent display of said written input of an electronic device (). The electronic device () has a touch input screen (), said touch input screen operable to accept written input, a display element (), said display element () operable to display one or more of recognized text and digital ink. The recognized text is determined from the written input using a recognition feature coupled to the touch input screen () while the digital ink corresponds to the written input. The digital ink may be edited by the user. A scrolling mechanism is coupled to the touch input screen () that enables at least a portion of the touch input screen () to appear to move as written entries are input thereon so as to continuously present screen space on the touch input screen () to the user for written input.

Method and system for message and note composition on small screen devices

A handheld devicewith a graphical user interface for entering handwritten text. The handheld device includes word and character input areaswithin a designated input area. Iconsandare disposed at the right side of the handwriting user interface. A scroll barmay be disposed at the right side of the interface display. An entry that begins in the word input areais treated as a handwritten word. A handwritten entry that begins in the character input areais treated as a single character and may be one character in character string. Handwritten character entries are each matched against all potential characters.

Text input method for personal digital assistants and the like

A handheld device such as a personal digital assistant (PDA) or the like, a handwritten input user interface (HIUI), a method of interfacing handwritten text and a program product therefor. A lower portion of a touch enabled display is designated as a handwriting input area Action icons and are disposed at a right side of the handwriting user interface Recognized text is displayed on the screen in a text display area located between a file management tool bar and the handwritten input area A scroll bar is disposed at the right side of the display As text is continuously entered each individual word may be recognized, and inserted into the end of the text stream. A word separator may demarcate or bracket individual words in a continuous input stream. A secondary list of potential recognition candidates may be available for display in a box and offered for substitution for or in lieu of the recognized word. Handwritten text may be continuously entered and displayed in the handwriting input area as digital ink, the input point staying approximately fixed with the ink display automatically scrolling. The input area behaves as a &ldquo;treadmill&rdquo; or &ldquo;ticker tape&rdquo; that is moving from right to left, thereby giving the illusion of a continuous writing space. The speed of the &ldquo;treadmill&rdquo; automatically adapts to writing speed. The device may include a communications function and, in particular the device may include an antenna for wireless communication. Individual function switches, buttons and other controls are disposed about the device.

Automatically scrolling handwritten input user interface for personal digital assistants and the like

Handwritten ink is scanned to identify potential diacriticals. A list of diacriticals ( ) is generated by traversing the ink. Potential diacritical-containing characters are processed by scoring them with and without a diacritical to generate a first and second score. The first score is compared to the second score to in order to make a decision as to which variant of the potential diacritical-containing character produced a highest score. The highest score is used as a score for a theory and the decision is recorded. A data structure ( ) is added to the theory. Each data unit in the data structure ( ) corresponds to an entry in the list of diacriticals ( ). As a new theory is created by propagation, contents of the data structure ( ) are copied into the new theory. Thus, the data structure ( ) is used to ensure that all handwritten ink is used and is used only once.

Diacritical processing for unconstrained, on-line handwriting recognition using a forward search

In a method of recognition of handwritten input, a preprocessing module (,) of a recognizer (,) having a recognition module (,), segments handwritten input into strokes, to provide stroke vectors. A search module (,) generates hypothetical character strings for scoring by the recognition module (,). A character hypothesis is generated which is a data set of a character, a start vector and an end vector. The recognizer (,) provides a non-cumulative score for the character hypothesis, where the score represents a likelihood of the character being present in the handwritten input at a position starting at the start vector and ending at the end vector. The recognizer (,) delivers to the search module a result that is either the score for the selected first character hypothesis or a result that allows the search module to temporarily ignore the hypothesis or to kill it altogether. The search module maintains or disregards the first hypothetical character string dependent on the result. The process is repeated for other character hypotheses and other hypothetical character strings.

Growing community of inventors

Mountain View, CA, United States of America

Giovanni Seni