Computers May Soon Know You Better Than Your Spouse
IDG News Service (01/12/15) Joab Jackson
Researchers at the University of Cambridge and Stanford University say they have developed a statistical modeling program that analyzes a user's likes on Facebook to characterize their personality with an accuracy rivaling that of a spouse or close family member. The researchers say the technique could help software interact with people in more meaningful ways than existing big data-based systems, which they say often make predictions that are narrow in their scope. The researchers sampled Facebook pages from 86,220 volunteers, many of whom also filled out a personality survey focused on five major psychological traits: openness, conscientiousness, extraversion, agreeableness, and neuroticism. The researchers conducted several rounds of machine learning to associate the traits with additional Facebook likes. To measure the effectiveness of the algorithms, the researchers gave questionnaires to friends and relatives of some participants. The survey results and computerized assessments then were compared with the self-assessments from the subjects. The researchers found that with just 10 likes the program would know someone as well as a work colleague, with more than 70 likes it reached the level of a friend or roommate, and with more than 300 likes it reached the level of a spouse or close relative.
IDG News Service (01/12/15) Joab Jackson
Researchers at the University of Cambridge and Stanford University say they have developed a statistical modeling program that analyzes a user's likes on Facebook to characterize their personality with an accuracy rivaling that of a spouse or close family member. The researchers say the technique could help software interact with people in more meaningful ways than existing big data-based systems, which they say often make predictions that are narrow in their scope. The researchers sampled Facebook pages from 86,220 volunteers, many of whom also filled out a personality survey focused on five major psychological traits: openness, conscientiousness, extraversion, agreeableness, and neuroticism. The researchers conducted several rounds of machine learning to associate the traits with additional Facebook likes. To measure the effectiveness of the algorithms, the researchers gave questionnaires to friends and relatives of some participants. The survey results and computerized assessments then were compared with the self-assessments from the subjects. The researchers found that with just 10 likes the program would know someone as well as a work colleague, with more than 70 likes it reached the level of a friend or roommate, and with more than 300 likes it reached the level of a spouse or close relative.
Colleges Rush to Create Cybersecurity Soldiers
Tampa Tribune (FL) (01/11/15) Jerome R. Stockfisch
The recent increase in computer attacks at major corporations have pushed colleges and universities into educating more cybersecurity students and professionals. For example, the University of Tampa (UT) recently announced it will begin offering an undergraduate major in cybersecurity this fall, while Saint Leo University launched a master's program in cybersecurity in August, complementing its undergraduate program in information assurance and security. In addition, Florida Polytechnic University has a concentration in information assurance and cybersecurity in its computer science and information technology degree track, and the University of South Florida opened the Florida Cybersecurity Center with the help of a $5-million allocation from the state government. "With all of the high-profile breaches over this last year or so, more focus has been on security than I've ever seen," says UT professor Kenneth Knapp, head of the university's cybersecurity program. There were 209,749 national postings for cybersecurity jobs in 2013, up 74 percent from 2007, and the average salary for those jobs was $93,028, according to Burning Glass. "For us, it's trying to keep up with the demand," says Derek Mohammed, chairman of the computer science department at Saint Leo. Interest in the university's inaugural master's program in cybersecurity has been double what was expected.
Tampa Tribune (FL) (01/11/15) Jerome R. Stockfisch
The recent increase in computer attacks at major corporations have pushed colleges and universities into educating more cybersecurity students and professionals. For example, the University of Tampa (UT) recently announced it will begin offering an undergraduate major in cybersecurity this fall, while Saint Leo University launched a master's program in cybersecurity in August, complementing its undergraduate program in information assurance and security. In addition, Florida Polytechnic University has a concentration in information assurance and cybersecurity in its computer science and information technology degree track, and the University of South Florida opened the Florida Cybersecurity Center with the help of a $5-million allocation from the state government. "With all of the high-profile breaches over this last year or so, more focus has been on security than I've ever seen," says UT professor Kenneth Knapp, head of the university's cybersecurity program. There were 209,749 national postings for cybersecurity jobs in 2013, up 74 percent from 2007, and the average salary for those jobs was $93,028, according to Burning Glass. "For us, it's trying to keep up with the demand," says Derek Mohammed, chairman of the computer science department at Saint Leo. Interest in the university's inaugural master's program in cybersecurity has been double what was expected.
Next-Gen Rust Language Moves to 1.0 Alpha
InfoWorld (01/12/15) Paul Krill
The Rust programming language has reached the stage of a feature-complete 1.0 alpha release. Developed by Mozilla Research, Rust is designed to be a fast systems programming language that will prevent most crashes, and the Rust Core Team describe the alpha release as a "huge milestone" for the language. "All 1.0 language features are now in place, and we do not expect major breaking changes to them," the team says. Developers have established application programming interface conventions, and have stabilized core functionality, including traits, data structures, and concurrency primitives. The beta1 release for Rust is expected the week of Feb. 16, and the general 1.0 version will likely follow one or more subsequent six-week release cycles. There should be minimal changes to the code that compiles on the beta release and on the final 1.0 version. However, the Rust team expects big changes in path and IO reform. The alpha release includes dynamically sized types, in which types whose size is only known at runtime are largely integrated into the language; multi-dispatch traits, in which trait deployments can be chosen via multiple types; associated types, which reduce verbosity with generics in traits; and where clauses, which offer a new way of specifying trait bounds.
InfoWorld (01/12/15) Paul Krill
The Rust programming language has reached the stage of a feature-complete 1.0 alpha release. Developed by Mozilla Research, Rust is designed to be a fast systems programming language that will prevent most crashes, and the Rust Core Team describe the alpha release as a "huge milestone" for the language. "All 1.0 language features are now in place, and we do not expect major breaking changes to them," the team says. Developers have established application programming interface conventions, and have stabilized core functionality, including traits, data structures, and concurrency primitives. The beta1 release for Rust is expected the week of Feb. 16, and the general 1.0 version will likely follow one or more subsequent six-week release cycles. There should be minimal changes to the code that compiles on the beta release and on the final 1.0 version. However, the Rust team expects big changes in path and IO reform. The alpha release includes dynamically sized types, in which types whose size is only known at runtime are largely integrated into the language; multi-dispatch traits, in which trait deployments can be chosen via multiple types; associated types, which reduce verbosity with generics in traits; and where clauses, which offer a new way of specifying trait bounds.
No comments:
Post a Comment